Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 83 for “"speech technology"”.

  1. Towards unsupervised speech technology with fewer resources

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for Towards unsupervised speech technology with fewer resources (opens in a new tab)

  2. Unsupervised speech technology for low-resource languages

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms

    uiuc Repository record for Unsupervised speech technology for low-resource languages (opens in a new tab)

  3. Unsupervised speech technology for low-resource languages

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms

    uiuc Repository record for Unsupervised speech technology for low-resource languages (opens in a new tab)

  4. Enhancing speech technology accessibility for individuals with Parkinson’s

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms

    uiuc Repository record for Enhancing speech technology accessibility for individuals with Parkinson’s (opens in a new tab)

  5. Representation Analysis Methods to Model Context for Speech Technology

    Speech technology has developed to levels equivalent with human parity through the use of deep neural networks. However, it is unclear how the learned dependencies within these networks can be attributed to metrics such as recognition performance. This research focuses on strategies to interpret …

    whiterose Download PDF for Representation Analysis Methods to Model Context for Speech Technology (opens in a new tab)

  6. Speech technology for monitoring disease progression in the context of neurodegenerative disease

    … of artificial intelligence (AI), particularly speech analysis, natural language processing and machine learning, offers opportunities for the automatic analysis of spoken language data. The work presented in this thesis applies an AI approach to the context of dementia, addressing three …

    edinburgh Repository record for Speech technology for monitoring disease progression in the context of neurodegenerative disease (opens in a new tab)

  7. Building personalised speech technology systems with sparse, bad quality or out-of-domain data

    Automatic speech recognition and text-to-speech systems offer handsfree and eyesfree interfaces for applications on computers, telephones and home and wearable electronics. The perceived quality and identity of a text-to-speech system's voice are essential to the user experience. The possibilities …

    aalto Repository record for Building personalised speech technology systems with sparse, bad quality or out-of-domain data (opens in a new tab)

  8. Speech Representations. Adventures in pre-training and fine-tuning transformers for speech technology tasks

    This thesis explores self-supervised speech representation learning, specifically focusing on the the wav2vec 2.0 framework. The research demonstrates that wav2vec 2.0, originally designed for automatic speech recognition, can be successfully fine-tuned for speaker recognition, even with limited …

    radboud Repository record for Speech Representations. Adventures in pre-training and fine-tuning transformers for speech technology tasks (opens in a new tab) Download PDF for Speech Representations. Adventures in pre-training and fine-tuning transformers for speech technology tasks (opens in a new tab)

  9. Exploring High-Variability Phonetic Training through Text-To-Speech Technology in ESL Pronunciation Pedagogy

    … that limit ESL learners’ exposure to varied speech sounds, hindering their pronunciation development. High-Variability Phonetic Training (HVPT) offers a potential solution by exposing learners in diverse speech sounds and accents to improve pronunciation skills. However, the practical …

    concordia Download PDF for Exploring High-Variability Phonetic Training through Text-To-Speech Technology in ESL Pronunciation Pedagogy (opens in a new tab)

  10. Toward a Social-Cognitive Psychology of Speech Technology: Affective Responses to Speech-Based e-Service

    Speech technologies, or technologies that recognize and respond to human speech, have recently emerged as a ubiquitous and cost-effective form of customer self-service (e-service). Although customer satisfaction is regarded as an important outcome of e-service interactions, little is known about …

    usf Repository record for Toward a Social-Cognitive Psychology of Speech Technology: Affective Responses to Speech-Based e-Service (opens in a new tab)

  11. Supporting Reading Comprehension of At-Risk Adolescent Readers Through the Use of Text-to-Speech Technology Paired with Strategic Instruction

    … This research highlighted the use of text-to-speech technology and current shifts in strategy-based reading instruction in order to address the comprehension needs of struggling pre-adolescent readers. The following questions were posed: (a) Does reading comprehension of preadolescent …

    ku Repository record for Supporting Reading Comprehension of At-Risk Adolescent Readers Through the Use of Text-to-Speech Technology Paired with Strategic Instruction (opens in a new tab)

  12. Rasch Modeling: Computer Assistive Technology In A High School Special Education Classroom

    … study guide questions when using assistive technology in a high school U.S. history class. The Rasch model was also used to estimate the quality of the study guide questions. The Rasch model was effective in analyzing the study guide questions. The study concluded that students with the …

    wayne-thes Repository record for Rasch Modeling: Computer Assistive Technology In A High School Special Education Classroom (opens in a new tab)

  13. Cross-regional word duration patterns in Mandarin

    … background, word structure, word frequency, speech genre, intention, and emotions. An understanding of duration lays the foundation for many aspects of speech technology since duration plays a major role in speech production and perception. This dissertation explores the duration patterns of …

    uiuc Repository record for Cross-regional word duration patterns in Mandarin (opens in a new tab)

  14. Intelligibility enhancement of casual speech based on clear speech properties

    … listener etc.) people adjust their speech in order to overcome the communication difficulty and successfully deliver their message. This remarkable adjustment produces different speaking styles compared to unobstructed speech (casual speech) that vary among speakers and conditions, …

    greece Repository record for Intelligibility enhancement of casual speech based on clear speech properties (opens in a new tab)

  15. Detection and Mitigation of Demographic Bias in Speech

    Speech technologies are now central to accessing services, information, and identity at scale, yet improvements in average accuracy have not brought equal performance for all users. Persistent gaps linked to gender, accent, race, age, and other factors remain in speech technology, affecting trust …

    jhu Repository record for Detection and Mitigation of Demographic Bias in Speech (opens in a new tab)

  16. Design and evaluation of mobile computer-assisted pronunciation training tools for second language learning

    The quality of speech technology (automatic speech recognition, ASR, and textto- speech, TTS) has considerably improved and, consequently, an increasing number of computer-assisted pronunciation (CAPT) tools has included it. However, pronunciation is one area of teaching that has not been developed …

    valladolid Repository record for Design and evaluation of mobile computer-assisted pronunciation training tools for second language learning (opens in a new tab)

  17. An algorithm for the assignment of lexical stress in converting text to speech

    … has been developed for inclusion in a text- to- speech conversion system. Within the field of speech technology, the correct assignment of lexical stress is important in ensuring that the correct rules of prosody are applied to the speech output. Some of the problems associated with word stress …

    uvic Repository record for An algorithm for the assignment of lexical stress in converting text to speech (opens in a new tab)

  18. Lexical and Acoustic Modelling of Swedish Prosody

    … are very important ingredients of human speech. In speech technology, text-to-speech (TTS) and automatic speech recognition (ASR) systems must incorporate prosodic models in order to reach acceptable performances. We contribute to the modelling of Swedish prosody in a speech technology …

    lund Repository record for Lexical and Acoustic Modelling of Swedish Prosody (opens in a new tab) Download PDF for Lexical and Acoustic Modelling of Swedish Prosody (opens in a new tab)

  19. Modulation domain processing and speech phase spectrum in speech enhancement

    Clean speech signal is often accompanied by various kinds of interferences, such as background noise, reverberation, and competing speech. These interferences degrade speech perceptual quality and intelligibility, and hamper speech technology applications. Conventional speech enhancement methods …

    missouri Repository record for Modulation domain processing and speech phase spectrum in speech enhancement (opens in a new tab)

  20. Computational differences between whispered and non-whispered speech

    Whispering is a common type of speech which is not often studied in speech technology. Perceptual and physiological studies show us that whispered speech is subtly di erent from phonated speech, and is surprisingly able to carry a tremendous amount of information. In this dissertation we con- sider …

    uiuc Repository record for Computational differences between whispered and non-whispered speech (opens in a new tab)

Page 1 of 5