To see the other types of publications on this topic, follow the link: End sound.
Journal articles on the topic 'End sound'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'End sound.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Hou, Lulu, Wenrui Duan, Guozhe Xuan, et al. "Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking." Sensors 23, no. 7 (2023): 3630. http://dx.doi.org/10.3390/s23073630.
Full textAbstract:
Wireless acoustic sensor networks (WASNs) and intelligent microsystems are crucial components of the Internet of Things (IoT) ecosystem. In various IoT applications, small, lightweight, and low-power microsystems are essential to enable autonomous edge computing and networked cooperative work. This study presents an innovative intelligent microsystem with wireless networking capabilities, sound sensing, and sound event recognition. The microsystem is designed with optimized sensing, energy supply, processing, and transceiver modules to achieve small size and low power consumption. Additionally, a low-computational sound event recognition algorithm based on a Convolutional Neural Network has been designed and integrated into the microsystem. Multiple microsystems are connected using low-power Bluetooth Mesh wireless networking technology to form a meshed WASN, which is easily accessible, flexible to expand, and straightforward to manage with smartphones. The microsystem is 7.36 cm3 in size and weighs 8 g without housing. The microsystem can accurately recognize sound events in both trained and untrained data tests, achieving an average accuracy of over 92.50% for alarm sounds above 70 dB and water flow sounds above 55 dB. The microsystems can communicate wirelessly with a direct range of 5 m. It can be applied in the field of home IoT and border security.
2
Li, Tao, Yibo Yin, Kainan Ma, Sitao Zhang, and Ming Liu. "Lightweight End-to-End Neural Network Model for Automatic Heart Sound Classification." Information 12, no. 2 (2021): 54. http://dx.doi.org/10.3390/info12020054.
Full textAbstract:
Heart sounds play an important role in the initial screening of heart diseases. However, the accurate diagnosis with heart sound signals requires doctors to have many years of clinical experience and relevant professional knowledge. In this study, we proposed an end-to-end lightweight neural network model that does not require heart sound segmentation and has very few parameters. We segmented the original heart sound signal and performed a short-time Fourier transform (STFT) to obtain the frequency domain features. These features were sent to the improved two-dimensional convolutional neural network (CNN) model for features learning and classification. Considering the imbalance of positive and negative samples, we introduced FocalLoss as the loss function, verified our network model with multiple random verifications, and, hence, obtained a better classification result. Our main purpose is to design a lightweight network structure that is easy for hardware implementation. Compared with the results of the latest literature, our model only uses 4.29 K parameters, which is 1/10 of the size of the state-of-the-art work.
3
Hegarty, Paul. "Noise threshold: Merzbow and the end of natural sound." Organised Sound 6, no. 3 (2001): 193–200. http://dx.doi.org/10.1017/s1355771801003053.
Full textAbstract:
When we ask what noise is, we would do well to remember that no single definition can function timelessly - this may well be the case with many terms, but one of the arguments of this essay is that noise is that which always fails to come into definition. Generally speaking, noise is taken to be a problem: unwanted sound, unorganised sound, excessively loud sound. Metaphorically, when we hear of noise being generated, we understand it to be something extraneous. Historically, though, noise has just as often signalled music, or pleasing sound, as its opposite. In the twentieth century, the notion of a clear line between elements suitable for compositional use (i.e. notes, created on instruments) and the world of noises was broken down. Russolo's ‘noisy machines’, Varèse and Satie's use of ostensibly non-musical machines to generate sounds, musique concrète, Cage's rethinking of sound, noise, music, silence . . .
4
Tran, Van-Thuan, Wei-Ho Tsai, Yury Furletov, and Mikhail Gorodnichev. "End-to-End Train Horn Detection for Railway Transit Safety." Sensors 22, no. 12 (2022): 4453. http://dx.doi.org/10.3390/s22124453.
Full textAbstract:
The train horn sound is an active audible warning signal used for warning commuters and railway employees of the oncoming train(s), assuring a smooth operation and traffic safety, especially at barrier-free crossings. This work studies deep learning-based approaches to develop a system providing the early detection of train arrival based on the recognition of train horn sounds from the traffic soundscape. A custom dataset of train horn sounds, car horn sounds, and traffic noises is developed to conduct experiments and analysis. We propose a novel two-stream end-to-end CNN model (i.e., THD-RawNet), which combines two approaches of feature extraction from raw audio waveforms, for audio classification in train horn detection (THD). Besides a stream with a sequential one-dimensional CNN (1D-CNN) as in existing sound classification works, we propose to utilize multiple 1D-CNN branches to process raw waves in different temporal resolutions to extract an image-like representation for the 2D-CNN classification part. Our experiment results and comparative analysis have proved the effectiveness of the proposed two-stream network and the method of combining features extracted in multiple temporal resolutions. The THD-RawNet obtained better accuracies and robustness compared to those of baseline models trained on either raw audio or handcrafted features, in which at the input size of one second the network yielded an accuracy of 95.11% for testing data in normal traffic conditions and remained above a 93% accuracy for the considerable noisy condition of-10 dB SNR. The proposed THD system can be integrated into the smart railway crossing systems, private cars, and self-driving cars to improve railway transit safety.
5
Zhang, Chengyun, Yonghuan Chen, Zezhou Hao, and Xinghui Gao. "An Efficient Time-Domain End-to-End Single-Channel Bird Sound Separation Network." Animals 12, no. 22 (2022): 3117. http://dx.doi.org/10.3390/ani12223117.
Full textAbstract:
Bird sounds have obvious characteristics per species, and they are an important way for birds to communicate and transmit information. However, the recorded bird sounds in the field are usually mixed, which making it challenging to identify different bird species and to perform associated tasks. In this study, based on the supervised learning framework, we propose a bird sound separation network, a dual-path tiny transformer network, to directly perform end-to-end mixed species bird sound separation in the time-domain. This separation network is mainly composed of the dual-path network and the simplified transformer structure, which greatly reduces the computational resources required of the network. Experimental results show that our proposed separation network has good separation performance (SI-SNRi reaches 19.3 dB and SDRi reaches 20.1 dB), but compared with DPRNN and DPTNet, its parameters and floating point operations are greatly reduced, which means a higher separation efficiency and faster separation speed. The good separation performance and high separation efficiency indicate that our proposed separation network is valuable for distinguishing individual birds and studying the interaction between individual birds, as well as for realizing the automatic identification of bird species on a variety of mobile devices or edge computing devices.
6
Nurillaeva, Mavlyuda Subhonovna. "Tables of prototype elements with losses of some chord sounds, with the synthesis of polyphonic circuits of a musical image." Multidisciplinary Journal of Science and Technology 4, no. 7 (2024): 17–21. https://doi.org/10.5281/zenodo.12630909.
Full textAbstract:
the article reveals a chord consisting of 3 sounds arranged in thirds. The sounds that make up a triad have their own names: the lower sound is prima or base, the middle is third or end sound, the upper is fifth or fifth sound. If the sounds of a triad are arranged in thirds, this is the main type of triad. A seventh chord is a chord consisting of four sounds that are or can be arranged in thirds. The interval between the two extreme sounds of a seventh chord is equal to a seventh, hence its name. When treating chords, composers did not specifically use thirds or fifths in order to diversify their music.
7
Loftin, Rayford A. "End weighted reed sound transducer." Journal of the Acoustical Society of America 84, no. 2 (1988): 803. http://dx.doi.org/10.1121/1.396727.
Full text
8
Hong, Xi, Bokai Du, Shuang Yang, Menghui Lei, and Xiangyang Zeng. "End-to-end sound field reproduction based on deep learning." Journal of the Acoustical Society of America 153, no. 5 (2023): 3055. http://dx.doi.org/10.1121/10.0019575.
Full textAbstract:
Sound field reproduction, which attempts to create a virtual acoustic environment, is a fundamental technology in the achievement of virtual reality. In sound field reproduction, the driving signals of the loudspeakers are calculated by considering the signals collected by the microphones and working environment of the reproduction system. In this paper, an end-to-end reproduction method based on deep learning is proposed. The inputs and outputs of this system are the sound-pressure signals recorded by microphones and the driving signals of loudspeakers, respectively. A convolutional autoencoder network with skip connections in the frequency domain is used. Furthermore, sparse layers are applied to capture the sparse features of the sound field. Simulation results show that the reproduction errors of the proposed method are lower than those generated by the conventional pressure matching and least absolute shrinkage and selection operator methods, especially at high frequencies. Experiments were performed under conditions of single and multiple primary sources. The results in both cases demonstrate that the proposed method achieves better high-frequency performance than the conventional methods.
9
Nirmalasari, Yohanna. "KESALAHAN BUNYI SIMAKAN PEMELAJAR BIPA TINGKAT PEMULA ASAL TIONGKOK." Tabasa: Jurnal Bahasa, Sastra Indonesia, dan Pengajarannya 1, no. 2 (2021): 147–64. http://dx.doi.org/10.22515/tabasa.v1i2.2692.
Full textAbstract:
Listening skills are language skills that affect the development of language learning, especially for second language learners. In the learning process of listening skills, mistakes often occur. This can happen because of the influence of the first language on the second language learning process. This study aims to describe the sound errors by observing beginner BIPA learners from China who do not use the alphabet in their first language. This research is a text analysis research which analyzes the sound errors by listening to BIPA students' writing. Based on the analysis that has been done, it can be concluded that there are three categories of sound errors, namely changes in the sound at the beginning of the word, the middle of the word, and the end of the word. Each of these categories has changes, omissions, and even added sounds. (1) In the mistakes at the beginning of words, learners make many mistakes in bilabial, dental, and velar inhibitory sounds. (2) For errors in the middle of a word, learners made many mistakes in inhibiting, nasal, vibrating, and lateral sounds, as well as removing nasal sounds and adding vibrating consonants. (3) In the error at the end of the word, the learner removes the final consonants of the inhibiting and fricative sounds, as well as changing the nasal sound, the fricative sound becomes a vibration, and the glotal fricative sound becomes a dental plosive sound.
10
Dronyaeva, Polina. "The “Sonic Flux” as Materialism Going to the End." Ideas and Ideals 16, no. 1-1 (2024): 103–28. http://dx.doi.org/10.17212/2075-0862-2024-16.1.1-103-128.
Full textAbstract:
The article analyses both the book of American philosopher Christoph Cox “Sonic Flux: Sound, Art and Metaphysics” and a wide range of critical publications dedicated to this book. The project “Sonic Flux” belongs to sonic materialism (a branch of “New Materialism’) also known as “Deleuzian sound studies”. For Cox this means a development of “immanent metaphysics” launched by G. Deleuze. But while continuing the project of Deleuze, Cox inherits his predicaments. Their range is as broad as the specter of Cox’s sources covering philosophy, arts, theory of perception. Debates around the project “Sonic Flux” highlighted such problems as the way Cox understands materialism and how he understands access to reality. Cox’s correlation of finite and infinite; particularity and universality, and anti-historicism are highly problematic for critics. Since Cox claims to develop a theory of sound art we assess his ideas from this perspective. This allows us to focus on modernism, anonymity and anti-humanism, central to Cox’s project but not to its criticism. A less important aspect – resentiment in Cox’s style – turned out to be helpful in drawing conclusions that the whole project “Sonic Flux” is built upon a range of assumptions. Cox himself names some of them while we indicated some others. The main conclusion of the article is the idea that the project “Sonic Flux” cannot provide an adequate theory of sound art nor contribute to sound studies because it is too embedded in the worst kind of modernism and structuralism. Such important notions of sonic materialism as autonomy and anonymity of sounds perfectly fit the tradition of Modernism while being completely alien to the sound studies.
11
A. R, Mashita Nadaa, Sitie Fithriyah, Muhammad Irfan Fathurrahman, and Rika Astari. "Variasi Fonologis Kosakata Bahasa Arab: Bahasa Arab Fushā dengan Bahasa Arab Maroko." Al-Ta'rib : Jurnal Ilmiah Program Studi Pendidikan Bahasa Arab IAIN Palangka Raya 8, no. 1 (2020): 65–76. http://dx.doi.org/10.23971/altarib.v8i1.1789.
Full textAbstract:
This study aims to explore phonological variations between the Arabic vocabulary of fusha and Moroccan Arabic. This article uses a qualitative method with a literature approach in expressing phenomena that develop, especially in the aspect of phonological variation between Arabic fusha and Moroccan Arabic. The results of this study reveal that there are several phonological variations in the Arabic vocabulary of Fusha with Moroccan Arabic namely: (1) Sound reinforcement such as changes in low vowel sound / a / into moderate vowel sound / e /, (2) Lattice like weakening high vowel sounds / u / become a low vowel sound / a /, (3) Monophonization such as the merging of vowel sounds / a / and / u / into a single vowel sound / o /, (4) Dating which is divided into three categories such as anheresis (dating that occurs in some vocabulary such as aħmaru, azraqu, and asˤfaru become Ħmar, zraq, and sˤfar by removing the vowel / a / at the beginning of a word), syncope (some dating of vowel sounds in the middle such as / a /, vowel / u / and / a /, and vowel / i /, and apokope (The dating of the sound at the end such as the word ʃamsun becomes ʃams, and the word ħamma: mun becomes ħamma: m, the word baħrun becomes baħr by removing the sound / un / at the end of the word).
12
Romei, Vincenzo, Micah M. Murray, Céline Cappe, and Gregor Thut. "The Contributions of Sensory Dominance and Attentional Bias to Cross-modal Enhancement of Visual Cortex Excitability." Journal of Cognitive Neuroscience 25, no. 7 (2013): 1122–35. http://dx.doi.org/10.1162/jocn_a_00367.
Full textAbstract:
Approaching or looming sounds (L-sounds) have been shown to selectively increase visual cortex excitability [Romei, V., Murray, M. M., Cappe, C., & Thut, G. Preperceptual and stimulus-selective enhancement of low-level human visual cortex excitability by sounds. Current Biology, 19, 1799–1805, 2009]. These cross-modal effects start at an early, preperceptual stage of sound processing and persist with increasing sound duration. Here, we identified individual factors contributing to cross-modal effects on visual cortex excitability and studied the persistence of effects after sound offset. To this end, we probed the impact of different L-sound velocities on phosphene perception postsound as a function of individual auditory versus visual preference/dominance using single-pulse TMS over the occipital pole. We found that the boosting of phosphene perception by L-sounds continued for several tens of milliseconds after the end of the L-sound and was temporally sensitive to different L-sound profiles (velocities). In addition, we found that this depended on an individual's preferred sensory modality (auditory vs. visual) as determined through a divided attention task (attentional preference), but not on their simple threshold detection level per sensory modality. Whereas individuals with “visual preference” showed enhanced phosphene perception irrespective of L-sound velocity, those with “auditory preference” showed differential peaks in phosphene perception whose delays after sound-offset followed the different L-sound velocity profiles. These novel findings suggest that looming signals modulate visual cortex excitability beyond sound duration possibly to support prompt identification and reaction to potentially dangerous approaching objects. The observed interindividual differences favor the idea that unlike early effects this late L-sound impact on visual cortex excitability is influenced by cross-modal attentional mechanisms rather than low-level sensory processes.
13
Nurjanah, Anisa, and Vivi Indriyani. "Types of Articulation Errors Produced by 3,5 Years Old Child: Study Case of PA." Jurnal Onoma: Pendidikan, Bahasa, dan Sastra 10, no. 3 (2024): 2527–34. http://dx.doi.org/10.30605/onoma.v10i3.3854.
Full textAbstract:
Articulation errors are often found in children. One of them is PA, 3.5 years old, a preschool student. This study aims to describe articulation errors shown by PA when communicating. This error will have a negative effect on PA if left without proper treatment. The author collected data by recording every word pronounced by PA according to the author's request. Then, the author pays attention to the articulation errors made and groups these errors into four types of articulation errors proposed by Fogle (2017). The author found three types of articulation errors that were often made by PA. PA shows a substitution error in the sound /s/ which changes to the sound /t/ if it is located at the end of the word. However, it changes to /c/ if it is located at the beginning and middle of a word. The sounds /r/ and /l/ change to /n/ when they are at the end of a word, but /r/ changes to /l/ when they are at the beginning and middle of a word. The /n/ sound will change to /ꬼ/ if it is in the middle of a word that has repeated sounds. The author also found omission errors, namely the sounds /g/, /k/, /d/, /j/ will be lost if they are at the beginning of the word. The sounds /l/ and /r/ will also disappear if they are in the middle of a word. Errors in adding sounds were found in the middle of words in the form of a nasal /m/ sound if followed by a /b/ sound and an /n/ sound if followed by a /d/ sound. Meanwhile, the sounds /n/ and /ꬼ/ will appear in the middle of words that have repeated sounds.
14
Guo, Binbin, Hong Tang, Shufeng Xia, Miao Wang, Yating Hu, and Zehang Zhao. "Development of a Multi-Channel Wearable Heart Sound Visualization System." Journal of Personalized Medicine 12, no. 12 (2022): 2011. http://dx.doi.org/10.3390/jpm12122011.
Full textAbstract:
A multi-channel wearable heart sound visualization system based on novel heart sound sensors for imaging cardiac acoustic maps was developed and designed. The cardiac acoustic map could be used to detect cardiac vibration and heart sound propagation. The visualization system acquired 72 heart sound signals and one ECG signal simultaneously using 72 heart sound sensors placed on the chest surface and one ECG analog front end. The novel heart sound sensors had the advantages of high signal quality, small size, and high sensitivity. Butterworth filtering and wavelet transform were used to reduce noise in the signals. The cardiac acoustic map was obtained based on the cubic spline interpolation of the heart sound signals. The results showed the heart sound signals on the chest surface could be detected and visualized by this system. The variations of heart sounds were clearly displayed. This study provided a way to select optimal position for auscultation of heart sounds. The visualization system could provide a technology for investigating the propagation of heart sound in the thoracic cavity.
15
ÇIĞ, Arzu, Arzu KOÇAK MUTLU, and Nazire MİKAİL. "A different factor in the use of plants in landscape architecture: Sound (type, intensity and duration) in the example of Hyacinthus orientalis L." Notulae Botanicae Horti Agrobotanici Cluj-Napoca 51, no. 3 (2023): 13271. http://dx.doi.org/10.15835/nbha51313271.
Full textAbstract:
The effect of music on people has been known for years and is still being researched from different aspects. The effects of music and sound waves on ornamental plants, whose effects on some vegetables, fruits and grains are examined, are also inquired. Especially the positive change in the development and showiness of the flowers of ornamental plant species with commercial importance will increase the market value of the plant. Again, with the effect of this sound wave, in order for the plants and their flowers to show the expected development, they should benefit from the planting environment and growing conditions at the maximum level. In the measurements taken from hyacinths (Hyacinthus orientalis L.) at the end of the duration that the plants were exposed to different types of sounds in different intensities, it was observed that these factors positively affected these parameters successively; 1 hour of bird sound in 50 dB, the number of leaves; 1 hour of bird sound in 90 dB, leaf width and floret length; 3 hours of bird sound in 70 dB, floret number; 3 hours of bird sound in 90 dB, the plant and flower height; 1 hour of bee sound in 50 dB, the stem thickness; 3 hours of vehicle sound in 50 dB, flower and floret width; 3 hours of vehicle sound in 70 dB, leaf length. At the end of the study, whereas it was determined that the bee sound had the least effect on the growth and flowering of the hyacinth, it was observed that the bird and vehicle sounds, that the plants were expose to in different intensities and durations, had a positive effect.
16
Hong, Joonki, Hai Tran, Jinhwan Jeong, et al. "0348 Sleep Staging Using End-to-End Deep Learning Model Based on Nocturnal Sound for Smartphones." Sleep 45, Supplement_1 (2022): A156—A157. http://dx.doi.org/10.1093/sleep/zsac079.345.
Full textAbstract:
Abstract Introduction Convenient sleep tracking with mobile devices such as smartphones is desirable for people who want to easily objectify their sleep. The objective of this study was to introduce a deep learning model for sound-based sleep staging using audio data recorded with smartphones during sleep. Methods Two different audio datasets were used. One (N = 1,154) was extracted from polysomnography (PSG) data and the other (N = 327) was recorded using a smartphone during PSG from independent subjects. The performance of sound-based sleep staging would always depend on the quality of the audio. In practical conditions (non-contact and smartphone microphones), breathing and body movement sounds during night are so weak that the energy of such signals is sometimes smaller than that of ambient noise. The audio was converted into Mel spectrogram to detect latent temporal frequency patterns of breathing and body movement sound from ambient noise. The proposed neural network model consisted of two sub-models. The first sub-model extracted features from each 30-second epoch Mel spectrogram and the second one classified sleep stages through inter-epoch analysis of extracted features. Results Our model achieved 70 % epoch-by-epoch agreement for 4-class (wake, light, deep, rapid eye movement) stage classification and robust performance across various signal-to-noise conditions. More precisely, the model was correct in 77% of wake, 73% of light, 46% of deep, and 66% of REM. The model performance was not considerably affected by existence of sleep apnea but degradation observed with severe periodic limb movement. External validation with smartphone dataset also showed 68 % epoch-by-epoch agreement. Compared with some commercially available sleep trackers such as Fitbit Alta HR (0.6325 in mean per-class sensitivity) and SleepScore Max (0.565 in mean per-class sensitivity), our model showed superior performance in both PSG audio (0.655 in mean per-class sensitivity) and smartphone audio (0.6525 in mean per-class sensitivity). Conclusion To the best of our knowledge, this is the first end (Mel spectrogram-based feature extraction)-to-end (sleep staging) deep learning model that can work with audio data in practical conditions. Our proposed deep learning model of sound-based sleep staging has potential to be integrated in smartphone application for reliable at-home sleep tracking. Support (If Any)
17
Soares, A. A., R. F. Cantão, J. B. Pinheiro Jr, and F. G. Castro. "Sound waves in a tube: measuring sound pressure profiles using smartphones." Physics Education 57, no. 5 (2022): 055023. http://dx.doi.org/10.1088/1361-6552/ac7cb4.
Full textAbstract:
Abstract We present an experiment designed to study standing waves in a tube with one closed end. Two smartphones are used, one to emit a sound signal with a chosen frequency and another equipped with a microphone to detect the sound pressure level inside the tube. Due to the finite diameter of the tube, the standing wave node (or antinode) appears slightly outside of its opened end so the end correction is applied. Results show a good agreement with the theory, making this proposal suitable to be applied to secondary school classes. It is a low cost experiment and has the potential to increase the understanding of this physical phenomenon by secondary students.
18
Li, Suyi, Feng Li, Shijie Tang, and Wenji Xiong. "A Review of Computer-Aided Heart Sound Detection Techniques." BioMed Research International 2020 (January 10, 2020): 1–10. http://dx.doi.org/10.1155/2020/5846191.
Full textAbstract:
Cardiovascular diseases have become one of the most prevalent threats to human health throughout the world. As a noninvasive assistant diagnostic tool, the heart sound detection techniques play an important role in the prediction of cardiovascular diseases. In this paper, the latest development of the computer-aided heart sound detection techniques over the last five years has been reviewed. There are mainly the following aspects: the theories of heart sounds and the relationship between heart sounds and cardiovascular diseases; the key technologies used in the processing and analysis of heart sound signals, including denoising, segmentation, feature extraction and classification; with emphasis, the applications of deep learning algorithm in heart sound processing. In the end, some areas for future research in computer-aided heart sound detection techniques are explored, hoping to provide reference to the prediction of cardiovascular diseases.
19
Hermintoyo, Muhamad. "Fungsi Rima dalam Lirik Lagu." Nusa: Jurnal Ilmu Bahasa dan Sastra 13, no. 1 (2018): 26. http://dx.doi.org/10.14710/nusa.13.1.26-35.
Full textAbstract:
The lyrics of a song as a creative piece of poetry are made up of physical and mental elements. Physical elements include diction, image, rhetorical means, and rhyme, while the inner element is the meaning. Rima or poetry in the lyrics (poetry) in addition to acting as aesthetics also provides a comfortable atmosphere, fun called eufofoni sound and provide euasana otherwise called kakophoni. Eufofoni sounds in the form of vowel sound, while the sound of kakofoni in the form of consonant sound. The sounds are deliberately chosen by the author as a means of rhetoric to be enjoyed in accordance with the meaning and theme contained in the lyrics. Rima in the lyrics (poetry) aesthetically gives the neatness of sound at the end of the stan neatly with the pattern aaaa (full), abab (cross), abba (hug), aabb (spouse) and broken (abcd).
20
Tyler, Richard S., A. J. Keiner, Kurt Walker, et al. "A Series of Case Studies of Tinnitus Suppression With Mixed Background Stimuli in a Cochlear Implant." American Journal of Audiology 24, no. 3 (2015): 398–410. http://dx.doi.org/10.1044/2015_aja-15-0005.
Full textAbstract:
Purpose Background sounds provided by a wearable sound playback device were mixed with the acoustical input picked up by a cochlear implant speech processor in an attempt to suppress tinnitus. Method First, patients were allowed to listen to several sounds and to select up to 4 sounds that they thought might be effective. These stimuli were programmed to loop continuously in the wearable playback device. Second, subjects were instructed to use 1 background sound each day on the wearable device, and they sequenced the selected background sounds during a 28-day trial. Patients were instructed to go to a website at the end of each day and rate the loudness and annoyance of the tinnitus as well as the acceptability of the background sound. Patients completed the Tinnitus Primary Function Questionnaire (Tyler, Stocking, Secor, & Slattery, 2014) at the beginning of the trial. Results Results indicated that background sounds were very effective at suppressing tinnitus. There was considerable variability in sounds preferred by the subjects. Conclusion The study shows that a background sound mixed with the microphone input can be effective for suppressing tinnitus during daily use of the sound processor in selected cochlear implant users.
21
Pauw, Andrea. "Eschatological Soundscapes: Morisco Poetry for the End Times." Calíope 30, no. 1 (2025): 22–42. https://doi.org/10.5325/caliope.30.1.0022.
Full textAbstract:
Abstract Copied by an Aragonese Morisco in the early seventeenth century, the Coplas sacadas de los castigos del hijo de Edam challenge the narrative of cultural decline often attributed to Moriscos. Attending to the poem’s oral and aural contexts of diffusion reveals efforts to preserve the sounds of the Qurʾān through a quintessential Castilian verse form and the Latin script. By reconsidering the ends and means of Morisco poetry from the perspective of sound and transliteration, this article invites critical engagement with a significant Morisco composition that has yet to receive its due in scholarship.
22
Musadin L., Kardanov. "The problem of determining the sound root and its semantics using the example of one sound of the Kabardino-Circassian language." Kavkazologiya 2025, no. 1 (2025): 275–85. https://doi.org/10.31143/2542-212x-2025-1-275-285.
Full textAbstract:
Additional analysis in determining the semantics of sound roots, which in Adyghe studies are con-sidered non-independent root elements, allows us to conclude that in the modern Kabardian-Circassian language, grammaticalized morphemes were once carriers of certain meanings. Based on the identified micro-meanings of sounds that allow us to decipher words, we put forward a hy-pothesis about the hierarchy of sounds in them, which is confirmed in examples from the lan-guage. This is a new approach not only in Adyghe studies but also in linguistics in general for de-termining the meaning of a word. The cardinal difference between our research and the followers of phonosymbolism is that, denying symbolism in sounds, we find its end-to-end meaning in all words of which it is a component and do not consider this the starting point for sound. We hypoth-esize that the absolute semantics of sound can only be determined at the intersection of linguistics and natural sciences. Our research establishes a viewpoint for identifying original and borrowed words, because many lexical units lack a reasoned multi-aspect analysis connecting them to a particular language.
23
Marshall, Steven E. "Low-frequency HVAC 'rumble' in a high-end condominium." INTER-NOISE and NOISE-CON Congress and Conference Proceedings 269, no. 1 (2024): 1092–97. http://dx.doi.org/10.3397/nc_2024_0146.
Full textAbstract:
Sound and vibration measurements were conducted at a high-end condominium located in downtown Washington DC. Data was collected within the client’s residence unit and on the building’s roof. The objective for the measurements was to identify and characterize the sound within the unit for which the resident had complained. The source of the sound in the bedroom was identified from vibration on a wall adjacent to an HVAC vertical duct. The sound and vibration were found to originate at a roof-mounted fan integral to the HVAC air distribution system. The character of the sound was modulating, low-frequency ‘rumble’. Further investigation on the roof, however, revealed the building’s structure to be adequately isolated from vibration due to the fan and motor. Rather, the sound was generated by the interaction of the fan’s aerodynamics and the acoustical properties of the vertical duct. The amplitude of the acoustic field in the duct was sufficient to excite vibration of the duct’s enclosing walls. Instead of modifying the structural geometry of the vertical duct, the most efficient ‘fix’ to attenuate duct rumble was by installing a silencer in the horizontal duct between the exhaust fan and the vertical duct.
24
Pinheiro, Sara. "Acousmatic Foley: Staging sound-fiction." Organised Sound 21, no. 3 (2016): 242–48. http://dx.doi.org/10.1017/s1355771816000212.
Full textAbstract:
This article proposes a narrative theory thought in terms that are specific to sound practice. It addresses two different fields – Acousmatic Music and Foley Art – as a possibility of understanding sound narration and conceptualising it around the idea of fiction. To this end, it begins from the concepts of sound-motif, sound-prop and sound-actors, in order to propose a dramaturgic practice specific to sound terms.The theory of sound dramaturgy acquires a practical outline by making use of multichannel constellations as a composition strategy, with specific loudspeaker arrangements. The theory advocates loudspeakers as the mediators of the experience and the stage as part of the audience’s assembly. This translates into a practice of staging sound fiction, which focuses on formulating a conjecture based on formal and factual structures, allowing for a direct relationship between the listener and the listening, between the sounds and their fictional location.
25
Muhammad Naqiuddin Zaini, Marina Yusoff, and Muhammad Amirul Sadikin. "Forest Sound Event Detection with Convolutional Recurrent Neural Network-Long Short-Term Memory." Journal of Advanced Research in Applied Sciences and Engineering Technology 32, no. 2 (2023): 242–54. http://dx.doi.org/10.37934/araset.32.2.242254.
Full textAbstract:
Sound event detection tackles an audio environment's complex sound analysis and recognition problem. The process involves localizing and classifying sounds mainly to estimate the start point and end points of the separate sounds and describe each sound. Sound event detection capability relies on the type of sound. Although detecting sequences of distinct temporal sounds is straightforward, the situation becomes complex when the sound is multiple overlapping of much single audio. This situation usually occurs in the forest environment. Therefore, this aim of the paper is to propose a Convolution Recurrent Neural Network-Long Short-Term Memory algorithm to detect an audio signature of intruders in the forest environment. The audio is extracted in the Mel-frequency cepstrum coefficient and fed into the algorithm as an input. Six sound categories are chainsaw, machete, car, hatchet, ambiance, and bike. They were tested using several epochs, batch size, and filter of the layer in the model. The proposed model can achieve an accuracy of 98.52 percent in detecting the audio signature with a suitable parameter selection. In the future, additional types of audio signatures of intruders and further aspects of evaluation can be added to make the algorithm better at detecting intruders in the forest environment.
26
IMAI, Yuki, and Keisuke YAMADA. "P083 Reduction of Radiated Sound from Duct End Using Piezoelectric Sound Absorbing Panel." Proceedings of Conference of Kansai Branch 2016.91 (2016): 456. http://dx.doi.org/10.1299/jsmekansai.2016.91.456.
Full text
27
Aswin, Muhammad, I. N. G. Wardana, Yudy Surya Irawan, and Hadi Suyono. "Bearing Damage Detection Based on Sound Signal." Applied Mechanics and Materials 548-549 (April 2014): 698–702. http://dx.doi.org/10.4028/www.scientific.net/amm.548-549.698.
Full textAbstract:
This paper presents a new method in damage detection by taking the sound signals of the rolling bearings in different levels. The tested bearing was put on the end of the shaft rotated by permanent magnet synchronous motor. The sound signal produced by this rig was recorded separately for each bearing condition with the same experimental environment. The sound data signals are compared each other. Based on the cross-correlation analysis, the recorded sound signal proved that the signals were recorded with the same environment. The power spectra calculation has shown different harmonic frequencies according to various bearing conditions. The total power of the sound is decreased along with the increasing damage. This is also confirmed by the auto-correlation of each sound signal that shows the appearance of the sounds impulse repetition with a wider period.
28
Ganina, Ch A., M. A. Kropotov, O. A. Saprina, et al. "Objective approach in the assessment of speech quality in patients with tongue cancer after hemiglossectomy." Head and Neck Tumors (HNT) 14, no. 2 (2024): 65–75. http://dx.doi.org/10.17650/2222-1468-2024-14-2-65-75.
Full textAbstract:
Introduction. Surgery is the leading treatment for tongue cancer, performance which leads to impaired speech function. Because speech is one of the most important tools of social interaction, its disorder can significantly affect patients’ quality of life. To date, there is no generally accepted objective approach to assessing the quality of speech that would make it possible to analyze speech changes at different stages of therapy and help in development of treatment strategy.Aim. To compare the sound reproduction of patients with tongue cancer after hemiglossectomy with and without reconstruction using an objective assessment method, namely – a special software.Materials and methods. The study included 29 patients who received surgical treatment in the volume of hemiglossectomy with ipsilateral cervical lymphodissection. The patients were divided into 2 groups: the group 1 included 14 patients who underwent reconstruction with submental, radial and buccal flaps, the group 2 – 15 patients who did not underwent it. Sound reproduction by each patient was recorded before the operation, no earlier than 10–12 days after it (session of type 1) and after the end of specialized treatment: radiation therapy, chemoradiation therapy (session of type 2). If adjuvant therapy was not prescribed, the type 2 session was performed 3–6 months after surgery. The records made during sessions of the types 1 and 2 were compared with records of preoperative session. During each session, the pronunciation of 30 syllables containing 3 problematic sounds was recorded: [k], [s] and [t] (10 syllables with each of the sounds). The differences in the data obtained during the sessions types 1 and 2 were analyzed according both the syllable set and separately for each sound studied.Results. The reconstruction performed improves sound pronunciation [t] after hemiglossectomy both after surgery and 3–6 months after the end of specialized treatment (p <0.01). After completion of specialized treatment, the pronunciation of the sound [s] significantly improved in both groups. However, in the reconstruction group, the variations in pronunciation values of this sound before the operation and after it obtained in the groups 1 and 2 were significantly reduced. During the assessment of the pronunciation of sound [k], the similar data were obtained. When comparing the quality of speech of patients during the type 2 session, the best results were obtained in group 1: in patients of this group, there were smaller mean differences in the sounds pronunciation as compared to the initial recording (p <0.001) than in patients of group 2.Conclusion. Resection of the tongue most negatively affects pronunciation of the dental-alveolar sounds than the whistling or palatine-dental sounds. The time factor has a positive effect on the speech quality of patients, therefore, the assessment of sound reproduction in patients after hemiglossectomy should be performed no earlier than 3–6 months after the end of specialized treatment.
29
Dai, Yuewei, Weiwei Liu, Guangjie Liu, Xiaopeng Ji, and Jiangtao Zhai. "An end-to-end generative network for environmental sound-based covert communication." Multimedia Tools and Applications 78, no. 7 (2018): 8635–53. http://dx.doi.org/10.1007/s11042-018-6592-2.
Full text
30
Abdoli, Sajjad, Patrick Cardinal, and Alessandro Lameiras Koerich. "End-to-end environmental sound classification using a 1D convolutional neural network." Expert Systems with Applications 136 (December 2019): 252–63. http://dx.doi.org/10.1016/j.eswa.2019.06.040.
Full text
31
Ambalegin, Ambalegin, and Tomi Arianto. "English Vowels and Consonants Mispronunciation of the Seventh President of Republic of Indonesia in His Official English Speeches and Its Influencing Factors." LANGUAGE LITERACY: Journal of Linguistics, Literature, and Language Teaching 2, no. 2 (2018): 113. http://dx.doi.org/10.30743/ll.v2i2.678.
Full textAbstract:
This research aimed to find out the mispronunciation of English vowels and consonants of the seventh president of Republic of Indonesia, Mr. Joko Widodo in his official English speeches based on the standard of British English Received Pronunciation (RP) and the factors influencing his English vowels and consonants mispronunciation. This research is a descriptive qualitative research. In collecting data, the researchers used observation method with non-participatory technique (Sudaryanto, 2015). In analyzing the data, the researchers used articulatory identity method (Sudaryanto, 2015). It was found that the consonant sounds /θ/, /ð/, /v/, /z/, /ʃ/ were pronounced incorrectly, the vowel sounds/ə/, /ɒ/, /ɛ/, /i/, /e/, /ɪ/ were pronounced inconsistently, and the diphthong sounds /ɪə/, /eɪ/, /əʊ/ and /aʊ/ were pronounced incorrectly. The consonant sound /l/ in the middle of the word was not pronounced. The consonant sound /j/ in the middle of the word is omitted. The consonant sounds /g/, /tʃ/, and /r/ were pronounced the same as the spelling. The consonant sounds /t/, /s/, /k/ at the end of the words were omitted. The letter y sounded /ɪ/ at the end of the word was pronounced as /e/. The diphthong sounds /ɪə/, /eɪ/, /əʊ/ and /aʊ/ were pronounced as /ɪ/, /ʌ/, /ɛ/, /ə/, /e/, and /ͻ/. The factors influencing the mispronunciation of English vowel and consonant sounds were mother tongue interference, sound system differences between Indonesian and English, the influence of spelling on pronunciation, educational background, and environmental background.
32
Atassi, Lilac. "Reducing the Effect of Imperfect Microphone and Speaker in Audio Feedback Systems." Leonardo Music Journal 29 (December 2019): 37–39. http://dx.doi.org/10.1162/lmj_a_01060.
Full textAbstract:
An audio feedback system that iteratively uses a room as a sound filter can be an artistic medium generating fascinating sounds. In this system, the room is not the only component acting as a filter. The sound system component, i.e. the speaker and microphone, also can have a sizeable impact on the sound in each iteration. To make sure the relative influence of the room on the sound is revealed and not masked by the audio system, the author proposes using a common calibration method at the end of each iteration. The mathematical model of the system is used to explain the reasoning behind the use of this method. Following this procedure, the author conducted an experiment that shows sound interaction with the room over time being captured in the artwork.
33
Oktira, Harisa Dwi, and Rahmadsyah Rangkuti. "PRONUNCIATION PROBLEM OF INDONESIAN LEARNERS IN PRONOUNCING /G/ SOUND AT BHAYANGKARI 01 SENIOR HIGH SCHOOL IN MEDAN." Hikari: Jurnal Bahasa dan Kebudayaan 1, no. 2 (2023): 80–87. http://dx.doi.org/10.37301/hikari.v1i2.15.
Full textAbstract:
Pronunciation is the production of sounds that are employed to convey meaning. Pronouncing English is a little bit difficult for Indonesian students since they use their mother tongue for their communication. This study was focused on the problem of pronunciation of the /g/ sound in English. The researcher used descriptive qualitative for the research design. The subject of research was the students in grade X MIA 3 that consisted of 27 students. The researcher used the purposive technique to take the sample of the research. The data collection of research was through observation, documentation, and diary notes. The researcher obtained five (5) types of problems in pronouncing /g/ sound, such as /g/ sound before /h/ at the end of words, /g/ sound before /n/ in the middle of words, /g/ sound before /n/ at the beginning of words, /g/ sounds before /e/ at the beginning of words, and /g/ sounds before /i/ at the beginning of words. The mean of data was 14.6, which suggested that there were about 15 students who had a good pronunciation. And the rest students were still had incorrect pronunciation.
34
Alexandraki, Chrisoula, Michael Starakis, Panagiotis Zervas, and Rolf Bader. "Inferring Drumhead Damping and Tuning from Sound Using Finite Difference Time Domain (FDTD) Models." Acoustics 5, no. 3 (2023): 798–816. http://dx.doi.org/10.3390/acoustics5030047.
Full textAbstract:
Percussionists use a multitude of objects and materials, mounted on their instruments, to achieve a satisfying sound texture. This is a tedious process as there are no guidelines suggesting how to manipulate a percussion instrument to adjust its perceptual characteristics in the desired direction. To this end, the article presents a methodology for computationally identifying how to damp and tune a drumhead by adjusting its mass distribution, e.g., by applying malleable paste on its surface. A dataset of 11,114 sounds has been synthesized using a FDTD solution of the wave equation representing the vibration of a membrane, which is being transmuted through the application of paste. These sounds are investigated to derive conclusions concerning their spectral characteristics and data reduction techniques are used to investigate the feasibility of computationally inferring damping parameters for a given sound. Furthermore, these sounds are used to train a Convolutional Neural Network to infer mass distribution from sound. Results show that computational approaches can provide valuable information to percussionists striving to adjust their personal sound. Although this study has been performed with synthesized sounds, the research methodology presents some inspiring ideas for future investigations with prerecorded sounds.
35
Chen, Yaxiong, and Xiaoqiang Lu. "A Deep Hashing Technique for Remote Sensing Image-Sound Retrieval." Remote Sensing 12, no. 1 (2019): 84. http://dx.doi.org/10.3390/rs12010084.
Full textAbstract:
With the rapid progress of remote sensing (RS) observation technologies, cross-modal RS image-sound retrieval has attracted some attention in recent years. However, these methods perform cross-modal image-sound retrieval by leveraging high-dimensional real-valued features, which can require more storage than low-dimensional binary features (i.e., hash codes). Moreover, these methods cannot directly encode relative semantic similarity relationships. To tackle these issues, we propose a new, deep, cross-modal RS image-sound hashing approach, called deep triplet-based hashing (DTBH), to integrate hash code learning and relative semantic similarity relationship learning into an end-to-end network. Specially, the proposed DTBH method designs a triplet selection strategy to select effective triplets. Moreover, in order to encode relative semantic similarity relationships, we propose the objective function, which makes sure that that the anchor images are more similar to the positive sounds than the negative sounds. In addition, a triplet regularized loss term leverages approximate l1-norm of hash-like codes and hash codes and can effectively reduce the information loss between hash-like codes and hash codes. Extensive experimental results showed that the DTBH method could achieve a superior performance to other state-of-the-art cross-modal image-sound retrieval methods. For a sound query RS image task, the proposed approach achieved a mean average precision (mAP) of up to 60.13% on the UCM dataset, 87.49% on the Sydney dataset, and 22.72% on the RSICD dataset. For RS image query sound task, the proposed approach achieved a mAP of 64.27% on the UCM dataset, 92.45% on the Sydney dataset, and 23.46% on the RSICD dataset. Future work will focus on how to consider the balance property of hash codes to improve image-sound retrieval performance.
36
He, Yuhang, Zhuangzhuang Dai, Niki Trigoni, Long Chen, and Andrew Markham. "SoundCount: Sound Counting from Raw Audio with Dyadic Decomposition Neural Network." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 11 (2024): 12421–29. http://dx.doi.org/10.1609/aaai.v38i11.29134.
Full textAbstract:
In this paper, we study an underexplored, yet important and challenging problem: counting the number of distinct sounds in raw audio characterized by a high degree of polyphonicity. We do so by systematically proposing a novel end-to-end trainable neural network~(which we call DyDecNet, consisting of a dyadic decomposition front-end and backbone network), and quantifying the difficulty level of counting depending on sound polyphonicity. The dyadic decomposition front-end progressively decomposes the raw waveform dyadically along the frequency axis to obtain time-frequency representation in multi-stage, coarse-to-fine manner. Each intermediate waveform convolved by a parent filter is further processed by a pair of child filters that evenly split the parent filter's carried frequency response, with the higher-half child filter encoding the detail and lower-half child filter encoding the approximation. We further introduce an energy gain normalization to normalize sound loudness variance and spectrum overlap, and apply it to each intermediate parent waveform before feeding it to the two child filters. To better quantify sound counting difficulty level, we further design three polyphony-aware metrics: polyphony ratio, max polyphony and mean polyphony. We test DyDecNet on various datasets to show its superiority, and we further show dyadic decomposition network can be used as a general front-end to tackle other acoustic tasks.
37
Alexander, Constance, and Sharon McKenna. "A Sound Partnership for End-of-Life Care." American Journal of Nursing 101, no. 12 (2001): 75–78. http://dx.doi.org/10.1097/00000446-200112000-00040.
Full text
38
Chen, Juan, Dinghao Wu, Andrew W. Appel, and Hai Fang. "A provably sound TAL for back-end optimization." ACM SIGPLAN Notices 38, no. 5 (2003): 208–19. http://dx.doi.org/10.1145/780822.781155.
Full text
39
Västfjäll, Daniel. "The “end effect” in retrospective sound quality evaluation." Acoustical Science and Technology 25, no. 2 (2004): 170–72. http://dx.doi.org/10.1250/ast.25.170.
Full text
40
EZZAT, Azza Adnan Ahmed. "TO TASTE THE SMELL OF LINGUISTIC SIGNIFICANCE AL-ALAQ SURAH AS A MODEL." International Journal of Humanities and Educational Research 03, no. 06 (2021): 90–100. http://dx.doi.org/10.47832/2757-5403.6-3.7.
Full textAbstract:
The linguistic miracle in the Nobel Qur´an has its own flavor, in terms of drawing, sound, formula, and structure. In Al-Alaq surah, we see the subject of the study, is that the first thing that draws attention to it is the congruence of the sounds of its name (Al-Alaq) and the meaning of its three paragraphs. The first paragraph in the first five verses of the surah, which talks about the beginning of creation, the beginning of learning, and the call to acquire knowledge. As for the second sound (al-lam), which is an approximant sound, repeated in the surah 43 times, it agrees with the second paragraph of the surah, which is the longest, and includes verses (6-14) that talk about the deviation of the unbelievers, and wonder about their actions, and determines four types of people towards the Da'wa. As for the third sound (qaf), which is a very explosive sound, it coincided with the third paragraph, which includes the last five verses (15-19) that challenges the deniers and describes their fate and severe torment. It is nice that these divisions coincided with the comma of the surah, as the first five verses and the last five verses ended with the closed sound syllable (CVC), while the nine verses in the middle of the surah (6-14) ended with the open sound syllable (CVV), and because the comma governed by the soothing pause, prompts us to contemplate the significance of the end. The end of the first five verses and the last five in this passage draws our attention to the intensity in the beginning and at the end of the surah; Therefore, we counted the percentage of the long open syllable (CVV), which gives a kind of feeling of temporal calm, and we found what reinforces this, as it represented (10.6%) in the first five verses and (17.64%) in the last five verses, as for the verses of the second paragraph. In the middle of the surah (6-14), its percentage reached (21.25%), in addition, the counting of the high explosive sounds that ended with the closed vocal syllables (CVC) in the three groups was consistent with that and reinforced it.
41
Kholidah, Umi, Dwi Fitriyani, Rohmah Tussoleha, and Laura Monica. "KESAMAAN BUNYI BAHASA TULIS AKSARA LAMPUNG DAN AKSARA BATAK TOBA SUMATERA UTARA." Bahtera Indonesia; Jurnal Penelitian Bahasa dan Sastra Indonesia 8, no. 2 (2023): 414–22. http://dx.doi.org/10.31943/bi.v8i2.429.
Full textAbstract:
This study aims to describe the similarities in the sounds of written language in the Lampung script and the Toba Batak script of North Sumatra. The method used is descriptive qualitative method. The results of the study show that there are several similarities in the sounds of written language in the Lampung script and the Toba Batak script. All the main letters of the Lampung script and Toba Batak script end in [a]. The entire sound of the Toba Batak script is exactly the same as the sound of the Lampung script, only the sound [ka] in the Lampung script is not found in the Toba Batak script. The sound of the children of this letter in the Batak Toba script [ng] and [h] has the same sound as the children of the Lampung script, namely Tekehole [ng] and Kelengiah [ah]. In conclusion, the similarities in the sound of written language in the Lampung script and the Toba Batak script can be seen from a historical background that both originate from India. The Lampung script comes from the Devanagari script and the Toba Batak script from Brahmi writing (India). Therefore, the Lampung script and the Toba Batak script have many similarities in the sound of their languages.
42
Li, Qian, Nan Li, Yan Wang, Zheng Li, Mengyun Tian, and Yihan Zhang. "Assessing Acoustic Conditions in Hybrid Classrooms for Chinese Speech Intelligibility at the Remote End." Buildings 15, no. 11 (2025): 1909. https://doi.org/10.3390/buildings15111909.
Full textAbstract:
Blended Synchronous Learning helps teachers and students communicate without geographical restrictions. The effect of communication between the face-to-face end and the remote end was not only affected by the performance of the equipment but also by the acoustic conditions in the classroom. This paper measured the acoustic parameters in the hybrid classrooms and conducted subjective speech intelligibility tests. It was found that for the hybrid classroom with a decentralized sound reinforcement system, the background noise level was high because lots of equipment was needed for synchronous learning. The speech intelligibility scores of the remote end were lower than those at the face-to-face end. Acoustic parameters of reverberation time (RT) and excessive signal-to-noise ratio (SNR) showed a negative correlation with speech intelligibility scores in the remote end. It was recommended that the sound pressure level (SPL) of the sound reinforcement system should not be too high and that appropriate sound absorption treatment be performed. The size of the hybrid classroom should be controlled to prevent the sound that arrived 50 ms after the direct sound from arriving. When SNR was 33 dB(A) for hybrid classrooms, which had a good performance in the face-to-face end with the speech intelligibility scores, T20 should be within 0.8 s to achieve the target value of 83% for SI scores at the remote end.
43
Haiyang Ni, Ning Wang, Ming Zhao, Bintao Deng, Shimin Wang, Xiaodan Ren,. "Research Of Singing With Note-name Recognition Algorithm Based On End-to-End Model." Journal of Electrical Systems 20, no. 2 (2024): 2106–12. http://dx.doi.org/10.52783/jes.1660.
Full textAbstract:
With the rapid development of artificial intelligence, and people are not only seeking material needs, but also pursuing happiness and spiritual aspirations. Especially some singing talent shows appear, but there are many controversial results. In order to solve the problem of singing with note-name evaluation and evaluate the singer's singing level in the professional music education of solfeggio and ear training, the paper uses artificial intelligence algorithms to recognize the note-name. Firstly, preprocess the singing sound data, including pre emphasis, framing, and windowing to reduce the impact of noise, and extract the acoustic features of the singing sound, the acoustic speech features are organized into a form suitable for DCNN input and a DCNN model is designed to obtain the pinyin form of the singing sound, the softmax layer adopts an end-to-end CTC structure, which classifies the input singing speech, finds corresponding phoneme sequences, and obtains the output results. The end-to-end CTC structure is used to classify and optimize the recognition process, and finally the state of the obtained features is output. And then singing pronunciation dictionary generates candidate word sequences based on the mapping relationship between phonemes and notes. Finally, based on the acoustic model score, the candidate note sequence with the highest score is obtained through decoder processing, and obtained the singing with note-name result of the singing sound. In order to further improve recognition performance, the paper introduces a new CTC-DCNN acoustic model. In this model, residual blocks can transfer input features to the output part through shortcuts, allowing the multi-layer convolutional speech features to be preserved as much as possible. At the same time, the deep structure can also better achieve the extraction and analysis of speech features. A new and improved CTC-DCNN acoustic model is obtained by optimizing the maxout function. The algorithm proposed in this paper is fair and equal in obtaining information, and no one participates in the entire process of obtaining scores. It is believed that the scoring results obtained in this way should be more objective.
44
Ali, Mad, Anwar Sanusi, Hikmah Maulani, et al. "Investigating the Arabic /f/ Pronunciation: A Comparative Analysis of Acoustic Phonetics." Al-Ta'rib : Jurnal Ilmiah Program Studi Pendidikan Bahasa Arab IAIN Palangka Raya 11, no. 2 (2023): 181–96. http://dx.doi.org/10.23971/altarib.v11i2.7234.
Full textAbstract:
This study aims to understand the mispronunciation of the consonant /f/ in Arabic by Javanese Speakers (JS), Sundanese Speakers (SS) and Batak Speakers (BS). The focus is on the sound /f/ as it can shift to /p/ when spoken by speakers of various L1 languages. Javanese, Sundanese, and Batak were chosen because of their prominence in Indonesia. Using a descriptive-evaluative-comparative approach, the researchers analyzed the pronunciation of /f/ by JS, SS, BS, contrasted with a native speaker (NS), Sheikh Misyari bin Rasyid Al-'Afasi. The research data was in the form of sound recordings of the recitation of nine verses of the Quran with the sound /f/, collected using the listen-record-pay-attention technique and analyzed acoustically through Praat. The findings reveal phonetic interference in pronouncing/f/ at the beginning, middle, and end of words by SS and BS. In JS, it only occurs at the beginning and the end. The absence of sound /f/ in the phonological system of local languages can cause this interference. The implication lies in learning to listen and speak Arabic, helping to design strategies to overcome pronunciation errors when encountering foreign sounds in the learner's phonological system.
45
Lluís, Francesc, Nils Meyer-Kahlen, Vasileios Chatziioannou, and Alex Hofmann. "Direction specific ambisonics source separation with end-to-end deep learning." Acta Acustica 7 (2023): 29. http://dx.doi.org/10.1051/aacus/2023020.
Full textAbstract:
Ambisonics is a scene-based spatial audio format that has several useful features compared to object-based formats, such as efficient whole scene rotation and versatility. However, it does not provide direct access to the individual source signals, so that these have to be separated from the mixture when required. Typically, this is done with linear spherical harmonics (SH) beamforming. In this paper, we explore deep-learning-based source separation on static Ambisonics mixtures. In contrast to most source separation approaches, which separate a fixed number of sources of specific sound types, we focus on separating arbitrary sound from specific directions. Specifically, we propose three operating modes that combine a source separation neural network with SH beamforming: refinement, implicit, and mixed mode. We show that a neural network can implicitly associate conditioning directions with the spatial information contained in the Ambisonics scene to extract specific sources. We evaluate the performance of the three proposed approaches and compare them to SH beamforming on musical mixtures generated with the musdb18 dataset, as well as with mixtures generated with the FUSS dataset for universal source separation, under both anechoic and room conditions. Results show that the proposed approaches offer improved separation performance and spatial selectivity compared to conventional SH beamforming.
46
Sullivan, Patrick. "Hanna-Barbera’s Cacophony: Sound Effects and the Production of Movement." Animation 16, no. 1-2 (2021): 21–35. http://dx.doi.org/10.1177/17468477211025660.
Full textAbstract:
Zaps, crashes, boinks, and bangs flooded TV’s airwaves with the rise of Hanna-Barbera Productions at the end of the 1950s, and these sound effects have been heard ever since. Hanna-Barbera Productions created and proliferated one of the most recognizable collections of sounds in television and animation history. This article traces the formation of Hanna-Barbera’s library of sound effects and how these sound effects operate within the studio’s cartoons. Motored by television’s demanding production schedule and restrictive budgets, Hanna-Barbera persistently recycled its sound effects across episodes, seasons, and series. These sound effects, heard over and over again, were paired to the studio’s brand of limited animation – a form of animation that is often seen as kinetically wanting – to enliven images through sonically invoking movement, what this article calls trajectory mimesis. This logic of trajectory mimesis facilitates the repetition of the studio’s sound effects. These conditions – television’s economic restraints and the studio’s limited animation aesthetics –provided the ideal conditions for the creation of Hanna-Barbera’s iconic library of sound effects.
47
Yang, Jingya, Yicheng Hsu, Jiaxuan Fan, et al. "Target-direction sound extraction using a hybrid DSP/deep learning approach." Journal of the Acoustical Society of America 156, no. 4_Supplement (2024): A25. https://doi.org/10.1121/10.0034980.
Full textAbstract:
The goal of Target Sound Extraction (TSE) is to isolate sound signals of interest from a mixture of overlapping sounds. In learning-based TSE approaches, the cues, such as sound embedding, which provide information about the sound characteristics, are used as auxiliary features for the Deep Neural Networks (DNNs) to extract the target sound signals. However, in the presence of strong interference, the extraction performance is reduced when the model relies solely on the sound embedding. To this end, this study proposes an efficient Target-Direction Sound Extraction (TDSE) system by integrating DSP-based spatial feature extraction and a DNN backend. In spatial feature extraction, the spatial blocking technique is used to analyze the signals out of the target direction. The DNN backend is based on the Waveformer backbone, which has shown promising results and real-time capability on single-channel TSE tasks. Experimental results show that the proposed TDSE system can achieve 2–3 dB improvement over the Waveformer baseline. In addition, the proposed system performs well on a variety of array setups, including those not included in the training set.
48
Tyler, Richard S., Rachael L. Owen, Julie Bridges, Phillip E. Gander, Ann Perreau, and Patricia C. Mancini. "Tinnitus Suppression in Cochlear Implant Patients Using a Sound Therapy App." American Journal of Audiology 27, no. 3 (2018): 316–23. http://dx.doi.org/10.1044/2018_aja-17-0105.
Full textAbstract:
Purpose The use of acoustic stimuli to reduce the prominence of tinnitus has been used for decades. Counseling and tinnitus sound therapy options are not currently widespread for cochlear implant (CI) users. The goal of this study was to determine whether tinnitus therapy sounds created for individuals with acoustic hearing may also benefit CI users. Method Sixteen sounds from the ReSound Relief app (Version 3.0) were selected for the study. Sixteen participants were asked to rate the overall acceptability of each sound and to write the description of the sound they perceived. Sounds were streamed from an Apple™ iPod (6th generation) to the CI using a Cochlear™ Wireless Mini Microphone 2+. Thirteen participants then completed a 5-min trial where they rated their pretrial and posttrial tinnitus and the acceptability of a subset of preferred sounds. Ten out of these 13 participants completed a 2-week home trial with a preferred sound after which they answered an online tinnitus questionnaire and rated the effectiveness of the sound therapy. Results Individual differences were large. Results from the 5-min trial showed that sounds perceived as rain, music, and waves were rated the most acceptable. For all of the participants, the posttrial tinnitus loudness rating was lower than the pretrial rating, with some participants experiencing greater difference in their tinnitus loudness than others. At the end of the 2-week home trial, 3 of 10 participants rated the effectiveness of sound therapy 70% or higher. Conclusion The results suggest that the use of tinnitus therapy sounds delivered through a CI can be acceptable and provides relief for some tinnitus sufferers.
49
Oknina, L. B., A. O. Kantserova, D. I. Pitshelauri, et al. "The Role of Midbrain in Perception of Tone Sequences and Speech: an Analysis of Individual Studies." Физиология человека 49, no. 4 (2023): 30–40. http://dx.doi.org/10.31857/s0131164623600052.
Full textAbstract:
Human speech is a complex combination of sounds, auditory events. To date, there is no consensus on how speech perception occurs. Does the brain react to each sound in the flow of speech separately, or are discrete units distinguished in the sound series, analyzed by the brain as one sound event. The pilot study analyzed the responses of the human midbrain to simple tones, combinations of simple tones (“complex” sounds), and lexical stimuli. The work is a description of individual cases obtained in the frame of intraoperative monitoring during surgical treatment of tumors of deep midline tumors of the brain or brain stem. The study included local-field potentials from the midbrain in 6 patients (2 women, 4 men). The S- and E-complexes that emerge at the beginning and end of the sound, as well as the S-complexes that emerge when the structure of the sound changes, were identified. The obtained data suggest that the selected complexes are markers of the primary coding of audio information and are generated by the structures of the neural network that provides speech perception and analysis.
50
Stutterheim, Kerstin. "Sound Dramaturgy." International Journal of Film and Media Arts 8, no. 3 (2023): 59–73. http://dx.doi.org/10.24140/ijfma.v8.n3.04.
Full textAbstract:
Sound dramaturgy as part of the aesthetic design of documentary films is invisible but most relevant, although often overlooked. The chapter gives a short introduction to dramaturgy and the importance of sound dramaturgy as most impactful for documentary film productions. The main discussion focusses on sound dramaturgy in films as The End Of Time (Mettler); The Island Of The Hungry Ghosts (Brady 2018), The Wale And The Raven (Leuze 2019) and El Sembrador de Estrellas (The Sower of Stars) by Lois Patiño. An analysis and discussion of the components of sound and music as part of the overall dramaturgical concept, the narrative flow, and their contribution to the final production and its sensual impact on the audience will allow a more informed understanding of such approach.