Academic literature on the topic 'Phonetic algorithm'

In this thesis, we aim to explore the combination of different lexical normalization methods and provide a practical lexical normalization pipeline for Swedish student writings within the framework of SWEGRAM(Näsman et al., 2017). An important improvement in my implementation is that the pipeline design should consider the unique morphological and phonological characteristics of the Swedish language. This kind of localization makes the system more robust for Swedish at the cost of being less applicable to other languages in similar tasks. The core of the localization lies in a phonetic algorithm we designed specifically for the Swedish language and a compound processing step for Swedish compounding phenomenon. The proposed pipeline consists of four steps, namely preprocessing, identification of out-of-vocabulary words, generation of normalization candidates and candidate selection. For each step we use different approaches. We perform experiments on the Uppsala Corpus of Student Writings (UCSW) (Megyesi et al., 2016), and evaluate the results in termsof precision, recall and accuracy measures. The techniques applied to the raw data and their impacts on the final result are presented. In our evaluation, we show that the pipeline can be useful in the lexical normalization task and our phonetic algorithm is proven to be effective for the Swedish language.

Approximate string matching consists in identifying strings as similar even ifthere is a number of mismatch between them. This technique is one of thesolutions to reduce the exact matching strictness in data comparison. In manycases it is useful to identify stream variation (e.g. audio) or word declension (e.g.prefix, suffix, plural). Approximate string matching can be used to score terms in InformationRetrieval (IR) systems. The benefit is to return results even if query terms doesnot exactly match indexed terms. However, as approximate string matchingalgorithms only consider characters (nor context neither meaning), there is noguarantee that additional matches are relevant matches. This paper presents the effects of some approximate string matchingalgorithms on search results in IR systems. An experimental research design hasbeen conducting to evaluate such effects from two perspectives. First, resultrelevance is analysed with precision and recall. Second, performance is measuredthanks to the execution time required to compute matches. Six approximate string matching algorithms are studied. Levenshtein andDamerau-Levenshtein computes edit distance between two terms. Soundex andMetaphone index terms based on their pronunciation. Jaccard similarity calculatesthe overlap coefficient between two strings. Tests are performed through IR scenarios regarding to different context,information need and search query designed to query on a technicaldocumentation related to software development (man pages from Ubuntu). Apurposive sample is selected to assess document relevance to IR scenarios andcompute IR metrics (precision, recall, F-Measure). Experiments reveal that all tested approximate matching methods increaserecall on average, but, except Metaphone, they also decrease precision. Soundexand Jaccard Similarity are not advised because they fail on too many IR scenarios.Highest recall is obtained by edit distance algorithms that are also the most timeconsuming. Because Levenshtein-Damerau has no significant improvementcompared to Levenshtein but costs much more time, the last one is recommendedfor use with a specialised documentation. Finally some other related recommendations are given to practitioners toimplement IR systems on technical documentation.

Orientador: Fabio Violaro<br>Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação<br>Made available in DSpace on 2018-08-11T22:49:44Z (GMT). No. of bitstreams: 1 Selmini_AntonioMarcos_D.pdf: 2404244 bytes, checksum: d7fcd0828f3157c595a0e3426b4a7eb0 (MD5) Previous issue date: 2008<br>Resumo: A demanda por uma segmentação automática de fala confiável vem crescendo e exigindo pesquisas para suportar o desenvolvimento de sistemas que usam fala para uma interação homem-máquina. Neste contexto, este trabalho relata o desenvolvimento e avaliação de um sistema para segmentação automática de fala usando o algoritmo de Viterbi e refinamento das fronteiras de segmentação baseado nas características fonético-acústicas das classes fonéticas. As subunidades fonéticas (dependentes de contexto) são representadas com Modelos Ocultos de Markov (HMM - Hidden Markov Models). Cada fronteira estimada pelo algoritmo de Viterbi é refinada usando características acústicas dependentes de classes de fones, uma vez que a identidade dos fones do lado direito e esquerdo da fronteira considerada é conhecida. O sistema proposto foi avaliado usando duas bases dependentes de locutor do Português do Brasil (uma masculina e outra feminina) e também uma base independente de locutor (TIMIT). A avaliação foi realizada comparando a segmentação automática com a segmentação manual. Depois do processo de refinamento, um ganho de 29% nas fronteiras com erro de segmentação abaixo de 20 ms foi obtido para a base de fala dependente de locutor masculino do Português Brasileiro.<br>Abstract: The demand for reliable automatic speech segmentation is increasing and requiring additional research to support the development of systems that use speech for man-machine interface. In this context, this work reports the development and evaluation of a system for automatic speech segmentation using Viterbi's algorithm and a refinement of segmentation boundaries based on acoustic-phonetic features. Phonetic sub-units (context-dependent phones) are modeled with HMM (Hidden Markov Models). Each boundary estimated by Viterbi's algorithm is refined using class-dependent acoustic features, as the identity of the phones on the left and right side of the considered boundary is known. The proposed system was evaluated using two speaker dependent Brazilian Portuguese speech databases (one male and one female speaker), and a speaker independent English database (TIMIT). The evaluation was carried out comparing automatic against manual segmentation. After the refinement process, an improvement of 29% in the percentage of segmentation errors below 20 ms was achieved for the male speaker dependent Brazilian Portuguese speech database.<br>Doutorado<br>Telecomunicações e Telemática<br>Doutor em Engenharia Elétrica

Made available in DSpace on 2014-06-11T19:29:40Z (GMT). No. of bitstreams: 0 Previous issue date: 2011-08-05Bitstream added on 2014-06-13T19:38:58Z : No. of bitstreams: 1 andrade_tl_me_sjrp.pdf: 1077520 bytes, checksum: 1573dc8642ce7969baffac2fd03d22fb (MD5)<br>Com o objetivo de garantir maior confiabilidade e consistência dos dados armazenados em banco de dados, a etapa de limpeza de dados está situada no início do processo de Descoberta de Conhecimento em Base de Dados (Knowledge Discovery in Database - KDD). Essa etapa tem relevância significativa, pois elimina problemas que refletem fortemente na confiabilidade do conhecimento extraído, como valores ausentes, valores nulos, tuplas duplicadas e valores fora do domínio. Trata-se de uma etapa importante que visa a correção e o ajuste dos dados para as etapas posteriores. Dentro dessa perspectiva, são apresentadas técnicas que buscam solucionar os diversos problemas mencionados. Diante disso, este trabalho tem como metodologia a caracterização da detecção de tuplas duplicadas em banco de dados, apresentação dos principais algoritmos baseados em métricas de distância, algumas ferramentas destinadas para tal atividade e o desenvolvimento de um algoritmo para identificação de registros duplicados baseado em similaridade fonética e numérica independente de idioma, desenvolvido por meio da funcionalidade multithreading para melhorar o desempenho em relação ao tempo de execução do algoritmo. Os testes realizados demonstram que o algoritmo proposto obteve melhores resultados na identificação de registros duplicados em relação aos algoritmos fonéticos existentes, fato este que garante uma melhor limpeza da base de dados<br>In order to ensure greater reliability and consistency of data stored in the database, the data cleaning stage is set early in the process of Knowledge Discovery in Database - KDD. This step has significant importance because it eliminates problems that strongly reflect the reliability of the knowledge extracted as missing values, null values, duplicate tuples and values outside the domain. It is an important step aimed at correction and adjustment for the subsequent stages. Within this perspective, techniques are presented that seek to address the various problems mentioned. Therefore, this work is the characterization method of detecting duplicate tuples in the database, presenting the main algorithms based on distance metrics, some tools designed for such activity and the development of an algorithm to identify duplicate records based on phonetic similarity numeric and language-independent, developed by multithreading functionality to improve performance over the runtime of the algorithm. Tests show that the proposed algorithm achieved better results in identifying duplicate records regarding phonetic algorithms exist, a fact that ensures better cleaning of the database

Resumo: Com o objetivo de garantir maior confiabilidade e consistência dos dados armazenados em banco de dados, a etapa de limpeza de dados está situada no início do processo de Descoberta de Conhecimento em Base de Dados (Knowledge Discovery in Database - KDD). Essa etapa tem relevância significativa, pois elimina problemas que refletem fortemente na confiabilidade do conhecimento extraído, como valores ausentes, valores nulos, tuplas duplicadas e valores fora do domínio. Trata-se de uma etapa importante que visa a correção e o ajuste dos dados para as etapas posteriores. Dentro dessa perspectiva, são apresentadas técnicas que buscam solucionar os diversos problemas mencionados. Diante disso, este trabalho tem como metodologia a caracterização da detecção de tuplas duplicadas em banco de dados, apresentação dos principais algoritmos baseados em métricas de distância, algumas ferramentas destinadas para tal atividade e o desenvolvimento de um algoritmo para identificação de registros duplicados baseado em similaridade fonética e numérica independente de idioma, desenvolvido por meio da funcionalidade multithreading para melhorar o desempenho em relação ao tempo de execução do algoritmo. Os testes realizados demonstram que o algoritmo proposto obteve melhores resultados na identificação de registros duplicados em relação aos algoritmos fonéticos existentes, fato este que garante uma melhor limpeza da base de dados<br>Abstract: In order to ensure greater reliability and consistency of data stored in the database, the data cleaning stage is set early in the process of Knowledge Discovery in Database - KDD. This step has significant importance because it eliminates problems that strongly reflect the reliability of the knowledge extracted as missing values, null values, duplicate tuples and values outside the domain. It is an important step aimed at correction and adjustment for the subsequent stages. Within this perspective, techniques are presented that seek to address the various problems mentioned. Therefore, this work is the characterization method of detecting duplicate tuples in the database, presenting the main algorithms based on distance metrics, some tools designed for such activity and the development of an algorithm to identify duplicate records based on phonetic similarity numeric and language-independent, developed by multithreading functionality to improve performance over the runtime of the algorithm. Tests show that the proposed algorithm achieved better results in identifying duplicate records regarding phonetic algorithms exist, a fact that ensures better cleaning of the database<br>Orientador: Carlos Roberto Valêncio<br>Coorientador: Maurizio Babini<br>Banca: Pedro Luiz Pizzigatti Corrêa<br>Banca: José Márcio Machado<br>Mestre

碩士<br>大同大學<br>資訊工程學系(所)<br>98<br>The need of using computer for physically disabled persons is no different from normal persons. Owing to the more dependency on computers for the former, the frequency of using computers is relatively more frequent, the period is even longer and, hence, the demand on human-factor engineering is much higher. The original design of computer interface is for normal users, traditional input devices, such as keyboard and mouse, require good hand-eye coordination to operate. For severe physically disabled persons with poor hand-eye coordination, it must be a big barrier. This thesis proposes the concept of full-view input method for mandarin words based on phonemes corresponding to valid phonetic-symbol combinations. The 418 mandarin phonemes of the 1st tone are simultaneously displayed in an input panel. Users can select the desirable phoneme and tone by dragging the cursor. This allows any phoneme of mandarin word to be selected in a single operation. With the help of special assistive technology device to simulate mouse device, physically disabled persons can greatly reduce the total number of operations needed to access any mandarin phoneme. This facilitates physically disabled persons to access a computer. The key point to successfully design such an input panel lies on the arrangement of phonemes. A reasonable arrangement must allow users to easily and quickly navigate to the desired phoneme. Using a computer to aid the design of input panel, the similarity or distance between each pair of phonemes must be properly defined. Accordingly, the object function of an input panel can then be defined for finding the optimal input panel. This research used genetic algorithm to search the optimal input panel. Experiment shows that the similar phonemes have the trend to clustering together in the resulting panel. Furthermore, coloring phonemes according to their auditory features is another way to facilitate users to locate the desirable phonemes. Extending the concept of the panel to other touch devices, such as digitizer, tablet PC, and IPAD, as input devices of mandarin words, in addition to benefit disabled people, normal users can be benefited as well.

This thesis addresses different aspects of machine listening using two different approaches, namely (1) A supervised and adaptive sparse representation based approach for identifying the type of background noise and the speaker and separating the speech and background noise, and (2) An unsupervised acoustic-phonetics knowledge based approach for detecting transitions between broad phonetic classes in a speech signal and significant excitation instants called as glottal closure instants (GCIs) in voiced speech, for applications like speech segmentation, recognition and modification. Real life speech signals generally contain a foreground speech by a particular speaker in the presence of a background environment like factory or traffic noise. These audio signals termed as noisy speech signals are available in the form of recordings say, audio intercepts or real time signals which can be single channel or multi channel. Real time signals are available during mobile communication and in hearing aids. Processing of these signals has been approached by the research community for various independent applications like classification of components of the noisy speech signal, source separation, enhancement, speech recognition, audio coding, duration modification and speaker normalization. Machine listening encapsulates solutions to these applications in a single system. It extracts useful information from noisy speech signals, and attempts to understand the content as much as humans do. In the case of speech enhancement, especially for the hearing impaired, the suppression of background noise for improving the intelligibility of speech would be more effective, if the type of background noise can be classified first. Other interesting applications of noise identification are forensics, machinery noise diagnostics, robotic navigation systems and acoustic signature classification of aircrafts or vehicles. Another motivation to identify the nature of background noise is to narrow down to the possible geographical location of a speaker. Speaker classification helps us to identify the speaker in an audio intercept. In the supervised sparse representation based approach, a dictionary learning based noise and speaker classification algorithm is proposed using a cosine similarity measure for learning atoms of the dictionary and is compared with other non-negative dictionary learning methods. For training, we learn dictionaries for speaker and noise sources separately using the various dictionary learning methods. We have used the Active Set Newton Algorithm (ASNA) and supervised non-negative matrix factorization for source recovery in the testing phase. Based on the objective measure of signal to distortion ratio (SDR), we get the frame-wise noise classification accuracy of 97.8% for fifteen different noises taken from the NOISEX database. The proposed evaluation metric of sum of weights (SW) applied on concatenated dictionaries gives a good accuracy, for speaker classification on clean speech, using high energy subsets of test frames and dictionary atoms. We get the best utterance level speaker classification accuracy of 100% for 30 speakers taken from TIMIT database on clean speech. We have then dealt with noisy speech signals assuming a single speaker speaking in a noisy environment. The noisy speech signals have been simulated at different SNRs using different noise and speaker sources. We have classified the speaker and background noise class of the noisy speech signal and subsequently separated the speech and noise components. Given a test noisy speech signal, a noise label is assigned to a subset of frames selected using the SDR measure, and an accumulated measure is used to classify the noise in the whole test signal. The speaker is classified using the proposed metric of accumulated sum of weights on high energy features, estimated using ASNA with L1 regularization from the concatenation of speaker dictionaries and the identified noise source dictionary. Using the dictionaries of the identified speaker and noise source, we obtain the estimate of the separated speech and noise signal using ASNA with L1 regularization and supervised non-negative matrix factorization (NMF). We obtain around 98% accuracy for noise classification and 89% for speaker classification at an SNR of 10 dB for a combination of 30 speakers and 15 noise sources. In the case of an unknown noise, the noise source is estimated as the nearest known noise label. The distribution of an unknown noise source amongst the known noise classes gives an indication of the possible noise source. The dictionary corresponding to the estimated noise label is updated adaptively using the features from the noise-only frames of the test signal. The updated dictionary is then used for speaker classification, and subsequently separation is carried out. In the case of an unknown speaker, the nearest speaker is estimated and the corresponding dictionary is updated using a clean speech segment from the test signal. We assume that a clean speech segment is available for adapting the speech dictionary. We have observed an improvement in signal to distortion ratio (SDR) after separation of speech and noise components using an adaptive dictionary. Adaptive noise dictionary gives an improvement of about 18% in speaker classification accuracy and 4 dB in SDR over an out-of-set dictionary, after enhancement of noisy speech at an SNR of 0 dB. In the case of a conversation, a divide and conquer algorithm is proposed to recursively estimate the noise sources, and estimate the approximate instant of noise transition and the number of noise types. We have then experimented on a conversation simulated by concatenating two different noise signals, each containing speech segments of distinct speakers and obtained a mean absolute error in the detection of noise transition instant of 10 ms at -10 dB SNR. Each of the segments obtained based on the transition instant can be treated as a single noise mixed with speech from a single speaker and subsequent speaker classification and source separation can be done as in the previous case. We have also addressed the classification of speakers and subsequent separation of speakers in overlapped speech, obtaining a mean speaker classification accuracy of 84% for the speaker 1 to speaker 2 ratio (S1S2R) of 0 dB. The advantage of the proposed dictionary learning and sparse representation based approach is that the training and classification model is independent of the selected classes of speakers and noises. Dictionaries for new classes can be easily added or the old classes can be removed or replaced instead of retraining. Also, the same model can be used for identifying other types of classes like language and gender. We have achieved speaker and noise classification and subsequent separation using only spectral features for dictionary learning. This is in contrast to the stochastic model based approaches where the model needs to be retrained whenever a new class is added. In the unsupervised acoustic-phonetics knowledge based approach, we detect transitions between broad phonetic classes in a speech signal which has applications such as landmark detection and segmentation. The proposed rule based hierarchical method detects transitions from silence to non-silence, sonorant to non-sonorant and vice-versa. We exploit the relative abrupt changes in the characteristics of the speech signal to detect the transitions. Relative thresholds learnt from a small development set are used to determine the parameter values. We propose different measures for detecting transitions between broad phonetic classes in a speech signal based on abrupt amplitude changes. A measure is defined on the quantized speech signal to detect transitions between very low amplitude or silence (S) and non-silence (N) segments. The S-segments could be stop closures, pauses or silence regions at the beginning and/or ending of an utterance. We propose two other measures to detect the transitions between sonorant and non-sonorant segments and vice-versa. We make use of the fact that most sonorants have higher energy in the low frequencies, than other phone classes such as unvoiced fricatives, affricates and unvoiced stops. For this reason, we use a bandpass speech signal (60-340 Hz) for extracting temporal features. A subset of the extrema (minimum or maximum amplitude samples) between every pair of successive zero-crossings and above a threshold is selected from each frame of the bandpass filtered speech signal. Occurrences of the first and the last extrema lie far before and after the mid-point (reference) of a frame, if the speech signal belongs to a non-transition segment; else, one of these locations lie within a few samples from the reference, indicating a transition frame. The advantage of this approach is that it does not require significant training data for determining the parameters of the proposed approach. When tested on the entire TIMIT database for clean speech, of the transitions detected, 93.6% are within a tolerance of 20 ms from the hand labeled boundaries. Sonorant, unvoiced non-sonorant and silence classes and their respective onsets are detected with an accuracy of about 83.5% for the same tolerance using the labelled TIMIT database as reference. The results are as good as, and in some respects better than the state-of-the-art methods for similar tasks. The proposed method is also tested on the test set of the TIMIT database for robustness with respect to white, babble and Schroeder noise, and about 90% of the transitions are detected within the tolerance of 20 ms at the signal to noise ratio of 5 dB. We have also estimated glottal closure instants (GCIs) useful for a variety of applications such as pitch and duration modification, speaking rate modification, pitch normalization, speech coding/ compression, and speaker normalization. The instant at which the vocal tract is significantly excited within each glottal cycle in a speech signal is referred to as the epoch or the GCI. Subband analysis of linear prediction residual (LPR) is proposed to estimate the GCIs from voiced speech segments. A composite signal is derived as the sum of the envelopes of the subband components of the LPR signal. Appropriately chosen peaks of the composite signal are the GCI candidates. The temporal locations of the candidates are refined using the LPR to obtain the GCIs, which are validated against the GCIs obtained from the electroglottograph signal, recorded simultaneously. The robustness is studied using additive white, pink, blue, babble, vehicle, HF channel noises for different signal to noise ratios and reverberation. The proposed method is evaluated using six different databases and compared with three state-of-the-art LPR based methods. The GCI detection performance of the proposed algorithm is quantified using the following measures: identification rate (IDR), miss rate (MR), false alarm rate (FAR), standard deviation of error (SDE) and accuracy to 0.25 ms. We have shown that significant GCI information exists in each subband of speech up to 2000 Hz, and a minimum of 89% identification rate (for subbands other than lowpass) can be obtained for clean speech using the proposed method. The results show that the performance of the proposed method is comparable to the best of the LPR based techniques for clean, and noisy speech.

This dissertation provides an analysis of reduction processes targeting Polish homorganic sequences of affricates + fricatives, in particular the alveolar sequence [ʦs] and the post-alveolar sequence [t͡šš]. These clusters have a long fricative phase, which consists of the fricative portion of an affricate and a full fricative phoneme. This long phase is dispreferred pre-consonantally. For example, the cluster [ʦs] is reduced in grójecki /grujɛʦ + ski/ → [grujɛʦki] (adj. from [grujɛʦ], a Polish place name), whereas the cluster [t͡šš] is reduced in the casual pronunciation of trzcina [t͡ššʨina] → [t͡šʨina] ‘cane’. Consequently, the clusters of affricates + fricatives are reduced to affricates. However, such reduction presents a challenge to categorical phonology because there is no mechanism to simplify the long fricative phase. Potentially degemination could eliminate the pre-consonantal length distinction, but the rule cannot target the long fricative phase due to the fact that the phase does not constitute a geminate in phonological sense. Reduction is motivated on phonetic grounds, but it displays features of a phonological rule. Consequently, the dissertation analyses reduction processes at the interface between phonetics and phonology. This dissertation is structured as follows. Chapter 1 provides a theoretical background for the discussion of reduction at the phonetics-phonology interface. Because the expectation is that [ʦs] and [t͡šš] reduction processes exhibit similar phonological and phonetic behaviour to other deletion/reduction processes in Polish, the chapter provides a discussion of two phonological deletion rules: Degemination and Strident Deletion with their phonostylistic equivalents. Moreover, the chapter argues for the monosegmental representation of affricates in order to exclude degemination as a viable solution to reduction. Chapter 2 presents the results of a study, which investigated the behaviour of [t͡šš] clusters in a variety of contexts, in two dialects of Polish with different intensity of reduction (high reduction in Silesian Polish and low reduction in Standard Polish). The motivation for the study was the lack of consistent and complete data in the existing literature. Chapter 3 provides theoretical approaches to the reduction of [t͡šš] clusters and argues that reduction in Silesian Polish is of phonological character. Consequently, intensive reduction is analysed within the framework of Standard Optimality Theory, whereas phonetic reduction in Standard Polish, due to its gradience, receives an analysis within Articulatory Phonology. Chapter 4 discusses the reduction of [ʦs] clusters. Unlike [t͡šš] reduction in Silesian Polish, [ʦs] reduction does not take place post-consonantally. Consequently, a different solution is offered which combines the models of Optimality Theory and Articulatory Phonology by making crucial use of gestural constraints. The dissertation also addresses the issue of free variation in reduction processes by employing the Gradual Learning Algorithm. Chapter 5 recapitulates this dissertation in the form of conclusions, highlighting the importance of the phonetics-phonology interface in reduction processes. Niniejsza rozprawa przedstawia analizę procesów redukcji spółgłoskowej w polskich zbitkach homorganicznych spółgłosek zwarto-szczelinowych i szczelinowych, w szczególności dziąsłowej zbitki [ʦs] oraz zadziąsłowej zbitki [t͡šš]. Te zbitki zawierają długą porcję głoski szczelinowej, która składa się z części głoski zwarto-szczelinowej oraz z pełnej głoski szczelinowej. Ta długa porcja jest skracana w kontekście przed spółgłoską. Na przykład, zbitka [ʦs] jest skracana w grójecki /grujɛʦ + ski/ → [grujɛʦki] (od Grójec [grujɛʦ]), a zbitka [t͡šš] jest skracana w potocznej wymowie słowa trzcina [t͡ššʨina] → [t͡šʨina]. Zatem zbitki głosek zwarto-szczelinowych i szczelinowych są upraszczane do głosek zwarto-szczelinowych. Jednakże taka redukcja stanowi problem dla kategorialnej fonologii, w obrębie której nie ma mechanizmu upraszczającego długą porcję głoski szczelinowej. Potencjalnie degeminacja mogłaby usunąć rozróżnienie długości dźwięków w kontekście przed spółgłoską, ale ta reguła nie dotyczy długiej porcji głoski szczelinowej, ponieważ ów porcja nie stanowi fonologicznej geminaty. Redukcja jest motywowana fonetycznie, jednakowoż prezentując cechy reguły fonologicznej. W związku z powyższym, niniejsza rozprawa analizuje procesy redukcji w interfejsie pomiędzy fonetyką a fonologią. Rozprawa ma następującą strukturę. Rozdział 1 przedstawia podłoże teoretyczne do dyskusji nad redukcją w interfejsie fonetyczno-fonologicznym. Ze względu na przypuszczenie, że redukcje zbitek [ʦs] i [t͡šš] przejawiają podobne zachowanie fonologiczne i fonetyczne względem innych procesów redukcji / elizji w polskim, rozdział przedstawia dyskusję na temat dwóch procesów elizji: degeminacji i elizji spirantów wraz z ich fonostylistycznymi odpowiednikami. Ponadto, rozdział przyjmuje monosegmentalną interpretację głosek zwarto-szczelinowych, aby wykluczyć degeminację jako potencjalne rozwiązanie problemu redukcji. Rozdział 2 przedstawia wyniki eksperymentu, który miał na celu zbadanie zachowania zbitek [t͡šš] w różnych fonetycznych kontekstach, w dwóch dialektach języka polskiego zróżnicowanych pod względem stopnia redukcji (intensywna redukcja w śląskim dialekcie i słaba redukcja w standardowej polszczyźnie). Badanie motywowane było deficytem danych o redukcji oraz brakiem spójnej i całkowitej analizy redukcji w dotychczasowej literaturze. Rozdział 3 przedstawia rozwiązania teoretyczne dla redukcji zbitek [t͡šš] i argumentuje za fonologiczną naturą redukcji w śląskim dialekcie. Zatem intensywna redukcja jest analizowana w Teorii Optymalności, podczas gdy fonetyczna słaba redukcja w standardowej polszczyźnie jest analizowana w Fonologii Artykulacyjnej. Rozdział 4 przedstawia zagadnienie redukcji zbitek [ʦs], które nie występują w kontekście po spółgłosce, w przeciwieństwie do redukcji zbitek [t͡šš] w dialekcie śląskim. Zatem przedstawione jest inne rozwiązanie, które łączy elementy Teorii Optymalności i Fonologii Artykulacyjnej poprzez zastosowanie warunków struktury gestów (gestural constraints). Rozprawa omawia również zagadnienie wariancji w procesach redukcji poprzez zastosowanie Algorytmu Stopniowego Uczenia się (Gradual Learning Algorithm). Rozdział 5 podsumowuje rozprawę, podkreślając znaczenie interfejsu fonetyczno-fonologicznego w procesach redukcji.