Dissertations / Theses on the topic 'Intelligent Voice Assistant'

This project includes an implementation of an intelligent voice recognition assistant for Android where functionality on current existing applications on other platforms is compared. Until this day, there has not been any good alternative for Android, so this project aims to implement a voice assistant for the Android platform while describing the difficulties and challenges that lies in this task.

The largest software companies in the world are racing to develop their Intelligent Personal Assistants. Each with more and more capabilities and ways for users to access them. The different assistants have different capabilities and one of the ways the companies are differentiating is in the interaction techniques their assistants that are controlled with, most uses voice, and some uses text. This thesis walks through these interaction techniques, give a brief overview of intelligent personal assistants today and explores how learnability differentiate when using these interaction techniques. The thesis also investigates when users have access to multiple interaction techniques to use in combination when interacting with such an assistant. To evaluate the field, a literature study was conducted covering Intelligent Personal Assistants, interaction techniques, conversational user interfaces, modalities, multimodal interaction, voice and chat interfaces. Interviews with early adopters of Intelligent Personal Assistants was performed to better understand the current state of the technology and how users were using it. To evaluate the learnability differences in different interaction techniques, a series of user tests in a wizard-of-oz setup was conducted. In the user tests the different groups was using different interaction techniques to interact with their assistants. The main findings of the user tests was that there are indications to that the type of language used differs depending on the interaction techniques. Users who interact through voice is more prone to use a more natural language, while users using a chat interface quickly started to treat the interactions with the Intelligent Personal Assistant as commands. The result observed was that users who interacted with the assistant using chat and then switched to interacting through voice used a shorter, more command-like language when they interacted through voice as well.

This thesis sets out to explore possible applications of speech recognition in construction equipment and autonomous machines. Advancements in autonomous vehicle technology mean that soon, vehicles like wheel loaders will be able perform tasks without human operators. Those vehicles still require a method of interaction with humans and recent improvements in speech recognition mean that it is possible for a natural voice-based interface to be used. The research question of this thesis is the extent to which voice control can replace hand-operated controls in an intelligent autonomous machine. Interviews and observation sessions took place in order to identify the requirements such a speech interface would have to fulfill. Next, a design process took place in order to build a prototype of such system, followed by test sessions to evaluate it. The prototype demonstrated positive attributes, with great learnability and ease of operation, but speech recognition errors meant low performance, and overall user satisfaction.
Detta examensarbete ämnar utforska möjliga tillämpningar av taligenkänning i byggutrustning samt självstyrande fordon. Framsteg i självstyrande fordonsteknologi visar att fordon som hjullastare kommer kunna utföra uppgifter själv, utan operatörer, inom kort framtid. I nuläget krävs ännu människor för att interagera med maskinen. Men nya framsteg i röststyrning visar att röstbaserade gränssnitt kan tillämpas. Forskningsfrågan i detta arbete är: Till vilken utsträckning kan röststyrning ersätta handmanövrerade instrument i ett intelligent självstyrt fordon? En etnografisk forskning ägde rum för att identifiera de krav som ett sådant gränssnitt skulle behöva uppfylla. En designprocess ägde rum för att utveckla en prototyp för ett sådant system. Prototypen utvärderades genom tester och påvisade positiva egenskaper. Den visade sig vara både lätt att lära samt enkel vid användning. Teknologin i taligenkänning påvisade dock brister genom dålig prestanda samt låg användarnöjdhet.

Modern teknik som intelligenta personliga assistenter (IPA) som finns i smartphones kan förenkla människors vardagliga liv. De kan hjälpa personer med funktionshinder och människor som lever stressfulla liv. Genom tal, kan IPA:er enkelt hjälpa personer som ofta har händerna fulla att hitta vägbeskrivningar, information eller skicka meddelanden över hela världen. För att locka människor till att förlita sig på IPA:er i det dagliga livet räcker det inte att den är intelligent och tilltalande, den måste också vara tillförlitlig. Det finns många faktorer som är involverade i att bygga ett trovärdigt system. Denna uppsats fokuserar på att ta reda på vilka egenskaper som gör en IPA:s röst trovärdig och vilken typ av röster designers bör göra tillgängliga för sina användare. Kvalitativa och kvantitativa forskningsmetoder har använts i studien. Sammanlagt 11 semi-strukturerade intervjuer genomfördes och varje innehöll ett kort användartest. 100 personer deltog i en enkätundersökning med ljudklipp och specifika frågor om egenskaper hos pålitliga IPA röster. 70 av 100 tillfrågade var överens om att röster som medför känslor, speciellt en känsla av trygghet och lugn, gör en IPA-röst trovärdig. Att låta tydlig, behaglig, människoliknande och erfaren, samt att ha en dialekt som användaren kan relatera till anses också vara viktiga röstegenskaper. Kön anses vara den minst viktiga.
Modern technologies such as intelligent personal assistants (IPA) found in smartphones can simplify the daily lives of people. They are not only useful for people with disabilities but also for those who live stressful lives. Through speech, IPAs can easily help a busy full-handed person find directions, information or send messages across the world. To entice people into relying on IPAs in their daily life, it not only has to be intelligent or appealing enough but also trustworthy. There are many principles involved in building a trustworthy system. This paper focuses on finding out what characteristics make an IPA-voice trustworthy and what kind of voices designers should make available for their users. Qualitative and quantitative research methods were used in the study. A total of 11 semi-structured interviews were carried out each in conjunction with a brief user test. 100 people participated in a survey with audio clips and specific questions regarding characteristics of trustworthy IPA-voices. 70 of 100 respondents agreed that voices that bring about emotions, particularly the feeling of security and tranquility, make an IPA-voice trustworthy. To sound clear, pleasant, human-like and experienced, and have a dialect that the user can relate to are also considered important voice qualities. Gender is considered the least important.

Conversational interfaces (CIs) have been a trending topic in recent years. As of the last decade, CIs have emerged with the aim of simplifying human-machine interactions and found a wide use case in the market. For example, Siri and Google Assistant are some of the most well-known CIs developed by the tech giants Apple and Google. The digital landscape has evolved from web, to mobile apps, to recently CIs. Nowadays, CIs, in particular chatbots and voicebots, are becoming increasingly common. Whether navigating the web or messaging on a phone, it is likely that CIs have been confronted offering the user help.However, CIs have not managed to reach a large-scale use. Furthermore, the reasons regarding the challenges faced by CIs as well as their usability are not greatly explored. In this thesis, we explore the most relevant uses of CIs and the reasons hindering a widespread use of CIs. Our goal is to provide an insight into CIs’ uses and list the reasons regarding the challenges faced by CIs. The research study followed a mixed method approach connecting an explorative qualitative literature study, a survey and an interview. The data was collected by using a systematic mapping approach for it being more suitable for conducting an effective literature review. The survey and the interview were conducted in order to confirm the findings.According to our research, it was found that the most common use cases of CIs were in customer service, sales, travel and bookings, education, healthcare and as voice assistants. The most prominent challenges faced by CIs were poor usability, language processing and understanding, speech recognition and natural language generation and security and privacy. As a conclusion, the future looks promising for CIs, however, they need to be furher researched and developed in order to help them reach a widespread use in the future.
Konversation Gränssnitt (CIs) har varit ett trendande ämne de senaste åren. Sedan det senaste decenniet har CIs kommit fram i syfte att förenkla interaktioner mellan människor och maskiner och har hittat ett brett användningsfall på marknaden. Det digitala landskapet har utvecklats från webb, till mobila appar till nyligen CI. Numera blir CIs, i synnerhet chatbots och voicebots, allt vanligare. Vare sig du navigerar på webben eller meddelanden i en telefon, är det troligt att CIs har konfronterats med att erbjuda användaren hjälp.CIs har dock inte lyckats uppnå storskalig användning. Dessutom är orsakerna till de utmaningar som CIs står inför och deras användbarhet inte utforskas i hög grad. I den här avhandlingen undersöker vi de mest relevanta användningarna av CIs och orsakerna till en utbredd användning av CIs. Vårt mål är att ge en inblick i CI: s användningar och lista orsakerna till de utmaningar som CIs står inför. Forskningsstudien följde en blandad metodstrategi som ansluter en utforskande kvalitativ litteraturstudie, en undersökning och en intervju. Uppgifterna samlades in med hjälp av en systematisk kartläggningsätt för att göra dem mer lämpliga för att genomföra en effektiv litteraturgranskning. Undersökningen och intervjun genomfördes för att bekräfta resultaten.Enligt vår forskning konstaterades att de vanligaste användningsfallen för CIs var kundservice, försäljning, resor och bokningar, utbildning, sjukvård och som röstassistenter. De mest framstående utmaningarna för CIs var dålig användbarhet, språkhantering och förståelse, taligenkänning och naturlig språkgenerering och säkerhet och integritet. Sammanfattningsvis ser framtiden lovande ut för CIs, men de måste undersökas och utvecklas ytterligare för att hjälpa dem att uppnå utbredd användning i framtiden.

From being a fictional element in sci-fi movies, voice user interaction has become reality with intelligent personal assistants like Apple’s Sir iand Google’s Assistant. The development opens up for new exciting user experiences and challenges when designing for these experiences. This thesis has aimed to investigate the user experience of different ways of onboarding new users to intelligent personalassistants. The process has included interviews with experienced users, a test of a Google Home for three months and a wizard of oz (WOZ) test. The interviews and the long term test was done in correlation with a literature study to determine how users interact with an intelligent personal assistant (IPA) their flaws, benefits, what added value they have etc. The goal of the WOZ test was to compare two different teaching methods during the onboarding of a new user. The methods were a voice tutorial by the IPA and a visual interaction on a mobile device. The outcome was to see if the users memory retention was different between the two methods for features learned during the test as well as the users opinions of the two different methods. The results from the interviews show that the benefits of using an IPA is in situations where it reduces friction, e.g when both hands are occupied. They also showed that there are still issues with IPAs and there is a long way to go before they can a accomplish a more human-to-human like conversation. In the WOZ test the results showed that there were no significant difference in user remembrance of learnt features between the two teaching methods. However the user insights showed that the majority of users would like to have a multimodal interaction, a combination of voice and visual interaction when being taught to use an IPA.

L'objectif principal de cette thèse est le développement et l'implantation d'une assistance active pour l'évitement des sorties involontaires de la voie de circulation. Les caractéristiques de cette assistance se déclinent ainsi : - intervention dans les moments d'inactivité du conducteur alors que la sortie de voie devient imminente et rétablissement de la situation de maintien de voie, - action partagée avec le conducteur sur la direction du véhicule, - fonctionnement sur des routes à faible et à forte courbure, - efficacité quelle que soit la qualité de la route, à forte ou à faible adhérence.

Background: E-commerce is widespread in today’s shopping routines and conversational commerce (CC) as an expansion, aims at integrating customers and businesses on a whole new level. Through the application of chatbots fueled by artificial intelligence, a more personal and individual way of remote shopping is offered. Purpose: Our research question What potential attributes of AI-fueled CC applications and their possible inherent characteristics are determining the willingness to use them and to what extent, in the context of digital natives living in Sweden and Germany? aims at identifying the demanded attributes of conversational commerce from a consumer perspective. Method: We facilitate a quantitative questionnaire with 118 valid answers to administer a traditional full-profile conjoint analysis. Conclusion: Our results indicate that German digital natives deem a CC application’s behavior as the most important attribute, followed by payment method, personality and communication form (voice or text). The Swedish digital natives however, attach the most importance to the payment method, followed by behavior, communication form and personality. Both have in common that they prefer a rather passive behavior over being actively approached, a personality that is balanced between humor and seriousness and text-based communication over voice. A difference is the Swedish preference for direct in-app payment while German digital natives would select a redirection to a secondary payment provider (e.g. PayPal).

В работе производиться анализ многоагентных интеллектуальных систем, их различия, способы и направления применения. Описываются программы и методы создания аудио управляемого синтеза лица. Также обсуждаются различные цифровые голосовые помощники, виртуальные агенты. Рассматривается гипотеза и перспективы создания визуального виртуального цифрового помощника для средств массовой информации.
The paper analyzes multi-agent intelligent systems, their differences, ways and directions of application. Programs and methods for creating audio-controlled face synthesis are described. Various digital voice assistants and virtual agents are also discussed. The hypothesis and prospects of creating a visual virtual digital assistant for mass media are considered.

碩士
國立交通大學
管理學院經營管理學程
105
The innovation business model has changed the industrial structure and its pattern, especially in competitive and rapidly changing markets. The role of jobs and positions in enterprise in the whole industry chain should be adjusted and replaced timely. Standing on the top of the enterprise, does not mean stand on the spot of the undefeated position, flourishing business examples are now visible everywhere. Hence, we have found that the enterprise competitive advantage has included: exploring their own advantages, combing with technology and understanding the flexibility to use resources and organizations with learning ability, and the spirit of innovation and conversion. Based on the above, this study was conducted on Amazon’s case of intelligent voice assistant products, and explores the industrial development and business model. In a highly competitive business environment, the product life cycle has been squeezed, the business industry is in the era of rapid conversion, the boundaries are blurring, and business cooperation is needed. Meanwhile, companies can not base their point of view solely on consumer needs of products and services. They need to understand market phenomenon, the full use of resources, and then work to arouse consumer demand and convenience, helping the enterprise build a good profit model.

碩士
國立交通大學
管理學院經營管理學程
106
After the smartphone industry has entered the sales plateau period, AI (artificial intelligence) is seen as an opportunity for the next wave of industrial revolution. Since the launching of Amazon Echo Smart Speaker by Amazon in 2014 to serve as a smart home entry system, no technological giants would ignore to actively catch up and develop AI intelligent voice assistants to layout the smart home market. This study is based on the research framework of UTAUT and UTAUT 2 to conduct an empirical research to explore the key factors affecting the consumer’s behavioral intention on using AI intelligent voice assistants. Moreover, age and AI intelligent voice assistant’s platform development type were adopted as moderating variables to serve as a reference for subsequent development of AI intelligent voice market products and marketing strategies. The results showed that: (1) Performance expectancy, effort expectancy, facilitating conditions, hedonic motivation, price value and habit affect consumer’s behavioral intention to use AI intelligent voice assistants. (2) Age differences moderate the effects of hedonic motivation and price value on AI intelligent voice assistants use intention. (3) The intelligent voice assistant’s platform development type differences moderate the effect of hedonic motivation on AI intelligent voice assistants use intention.

With the development of advanced technology, intelligent voice assistants (IVAs) have emerged as popular service devices. In the hospitality industry, major hotel chains have installed ‘Alexa for Hospitality’, a representative of IVAs, in guestrooms for customer service. Although the voice-based technology obtained huge attention of the public, there is little understanding of the factors that motivate people to use IVAs in hotel rooms. Additionally, mature travelers’ viewpoints towards this technology got less concern in the academic field, though the rapid growth of aging population makes mature adults a big part of guests staying at hotels.

Considering the forever evolving technology and the especially affected group – mature travelers, traditional technology acceptance theories may not be sufficient to achieve the goal of this study, an updated model is needed. Therefore, a mixed method approach including a qualitative interview and a quantitative study of an online survey is applied. The first stage is the qualitative interview which aims to improve the proposed conceptual model for a comprehensive understanding of mature travelers. An online survey is utilized to assess the conceptual model and the consequent hypotheses. The final model includes five determinants: performance expectancy, effort expectancy, social influence, self-efficacy and anxiety, as well as the mediator of trust that is discovered from the qualitative interview. The findings of the quantitative study show that mature travelers’ intention to use the IVAs at hotels is motivated by performance expectancy and social influence. Trust and behavioral intention partially mediate the relationship between these two variables. Effort expectancy and anxiety show no significant effect on mature travelers’ behavioral intention. This research contributes to the service technology literature with empirical evidences to delineate the behavioral pattern of this customer group. Managerially, the current research provides practical guidelines to the hospitality practitioner for a better understanding of a particular market segmentation: mature travelers.

The development of artificial intelligence (AI) devices, such as voice assistants, has been growing, and with that comes a growing curiosity about this matter. The objective of this research was to identify possible mediators between the experience a customer has with the brand and the willingness to use a voice assistant, as well as being able to verify what could be the possible outcomes of using the AI device and how it could impact the relationship between the customer and the brand. With the usage of a Google Assistant, an experiment was recorded and shared online, through a website on a platform called Wix, where different scenarios were simulated to allow the reach of relevant conclusions. By conducting this experiment, it was concluded that independently from the experience the customer had, or did not had, with the brand, the usage of voice assistants is highly influenced by the level of familiarity with the brand. It was also concluded that the usage of voice assistants can lead to feelings of compassion and love towards the brand, which can consequently lead to an affective commitment with the brand. In a time were managers in any industry are working for ways to improve and maintain their relationships with the customers, the present research shows how technology is a crucial part of any marketing action, even when using an AI device to strengthen customer brand relationships.
O desenvolvimento de equipamentos de inteligência artificial (IA), como os assistentes de voz, tem estado em crescente evolução, provocando uma curiosidade crescente acerca do tema. O objetivo desta tese é de identificar potenciais mediadores entre a experiência que o cliente tem com uma marca e a sua vontade de utilizar um assistente de voz, assim como indicar quais serão as consequências da utilização de um equipamento de IA e como é que a mesma pode impactar a relação entre o cliente e a marca. Recorrendo a um Google Assistant, foi gravada e partilhada uma experiência com o mesmo, através de um website na plataforma Wix, onde vários cenários foram simulados para que pudessem ser atingidas conclusões relevantes. Ao conduzir esta experiência, foi possível concluir que independentemente da experiência que o cliente teve, ou não, com a marca, a utilização do assistente de voz é altamente influenciada pelo grau de familiaridade que o consumidor tem com a mesma. Também foi possível concluir que a utilização de assistentes de voz pode levar a sentimentos de compaixão e amor pela marca, o que pode consequentemente levar a um compromisso afetivo para com a marca. Numa altura em que gestores de qualquer indústria trabalham para encontrar formas de melhorar e manter a relação com os seus clientes, o presente estudo mostra como a tecnologia é uma parte crucial de qualquer ação de marketing, mesmo no que toca à utilização de um equipamento de IA para fortalecer a relação entre a marca e os clientes.

Les assistants vocaux ont mis au jour une nouvelle manière pour l’humain d’interagir avec les technologies en n’utilisant que la voix. Une technologie qui est également évolutive et interactive grâce à l’intelligence artificielle. Nous verrons que les caractéristiques techniques et logicielles les composant concourent à une collecte massive de renseignements personnels par les entreprises. L’imprécision des politiques de confidentialité, l’absence d’information sur le mode de fonctionnement, l’imperfection du traitement automatique du langage naturel (ci-après le « TALN ») caractérisée par les faux positifs et les difficultés inhérentes à l’exercice par l’individu de certains de ses droits tendent à limiter l’effectivité des différentes lois existantes à l’assistant vocal. En outre, la possibilité pour plusieurs personnes d’interagir avec l’objet ainsi que son absence d’autonomie tendent à compliquer l’application des régimes de responsabilité civile, dont celui résultant du fait des biens. Cette apparition récente de l’assistant vocal n’a pour l’heure pas permis au juge de se prononcer pour faire évoluer les jurisprudences relatives au droit à la vie privée, à la protection des renseignements personnels et à la responsabilité civile. Celles déjà existantes ne semblent plus être adaptées à ce contexte technologique autour de l’assistant vocal, et plus généralement autour de la voix. C’est ainsi que le test de Oakes, permettant de déterminer le caractère raisonnable d’une violation des droits et libertés énoncés dans la Charte canadienne, repris pour être appliqué à la LPRPDE, apparaît comme étant inadapté à ce nouveau contexte technologique. Enfin, le manque de pouvoirs conférés aux autorités compétentes représente un obstacle majeur dans le suivi de l’application des règles de droit.
Voice assistants bring a new way for humans to interact with technology by only using their voice. Scalable and interactive technology thanks to artificial intelligence. We will see that the technical and software characteristics of voice assistants contribute to a massive collection of personal information by companies. The imprecision of confidentiality policies, the absence of information on the mode of operation, the imperfection of the Natural Language Processing characterized by false positives and the difficulties inherent in the exercise by individuals of some of their rights contribute to the mismatch between voice assistants and various existing laws. In addition, the possibility for people to interact with the object as well as its lack of autonomy tend to complicate the application of civil liability regimes, including that resulting from the act of thing. This recent appearance of voice assistants has so far not giving judges the possibility to rule on the right to privacy, protection of personal information and civil liability. Current case law doesn’t seem to be well adapted to the technological context around the voice assistant, and more generally the voice. The Oakes test, which was design to determining the reasonableness of a violation of the rights and freedoms set out in the Canadian Charter, appears to be unsuited to this new context. We will see that the lack of powers conferred on the competent authorities represents a major obstacle in monitoring the application of the rule of law.

Technology is significantly changing tourism experiences and hotel services. Voice-enabled devices are rapidly becoming the new home adoption standard to control home smart appliances and access voice information. This study aims to provide valuable insights from both the customers’ and hotel operators’ perspective upon the adoption of an In-Room Voice Assistant service for hospitality. This study analyzed and summarized previous research proposing a conceptual framework able to analyze the customers attitude and intention toward the technology. The study also investigates the relationship between perceived usefulness and intention-to-use moderated by localization, and the resulting behavioral intention as purchase intention and word-of-mouth in regard of the hotel services. We demonstrate that perceived usefulness positively affects intention to use which in turn positively affects purchase intention and word-of-mouth. Furthermore, localization is a statistically significant moderator of the relationship between perceived usefulness and intention-to-use, resulting as a valuable factor to take into account for communication issues. Moreover, in-depth interviews were conducted with three hotel and hospitality managers which further reinforced the results from the customer analysis study. Finally, findings and general discussion was assessed together with closing managerial implications, limitations and suggestions for further research.
A tecnologia está a mudar significativamente a experiência no turismo e nos serviços hoteleiros. O controlo por voz está a tornar-se comum na utilização doméstica para controlar equipamentos domésticos e aceder a informações. Este estudo tem como objetivo fornecer informações importantes sobre o potencial de adoção de um assistente de voz no quarto para hospitalidade, tanto para clientes como para gerentes de hotéis. Este estudo resumiu e analisou pesquisas anteriores, propondo uma estrutura conceptual para analisar a atitude e a intenção dos clientes em relação à tecnologia. Foi investigada a relação entre a utilidade percebida e a intenção de usar, a moderação por localização, e a intenção comportamental resultante como intenção de compra e word of mouth em relação aos serviços do hotel. Demonstramos que a utilidade percebida afeta positivamente a intenção de usar, o que, por sua vez, afeta positivamente a intenção de compra e a word of mouth. Além disso, a localização é moderadora estatisticamente significativa da relação entre a utilidade percebida e a intenção de usar, resultando num fator relevante para superar eventuais problemas de comunicação. Além disso, foram realizadas entrevistas em profundidade com três gerentes, que mostraram uma boa correspondência com os resultados da análise dos clientes. Finalmente, as conclusões e a discussão geral foram sintetizadas em termos de implicações gerenciais, limitações e sugestões para possíveis análises futuras.