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 48 for “"Synthesized speech"”.

  1. THE QUALITY OF SYNTHESIZED SPEECH USING LINEAR PREDICTIVE CODING ON FINITE WORDLENGTH INTEGRATED CIRCUITS.

    This paper studies the quality of synthetic speech produced by integrated circuit (IC) hardware using fixed-point arithmetic and Linear Predictive Coding (LPC). A theoretical model explaining the combined effects of finite wordlength and parametric model order is developed. This model is used to …

    arizona-thes Repository record for THE QUALITY OF SYNTHESIZED SPEECH USING LINEAR PREDICTIVE CODING ON FINITE WORDLENGTH INTEGRATED CIRCUITS. (opens in a new tab)

  2. The effects of speech rate, message repetition, and information placement on synthesized speech intelligibility

    Recent improvements in speech technology have made synthetic speech a viable I/O alternative. However, little research has focused on optimizing the various speech parameters which influence system performance. This study examined the effects of speech rate, message repetition, and the placement of …

    vt Repository record for The effects of speech rate, message repetition, and information placement on synthesized speech intelligibility (opens in a new tab)

  3. Synthesized speech intelligibility and preschool age children: comparing accuracy for single word repetition with repeated exposure.

    … environments on the intelligibility of two synthesized speech voices and human recorded speech in preschool age children. Methods: Eighteen preschool aged participants listened to and repeated single words presented in human recorded speech, DECtalk™ Paul and AT & T Voice ™ Michael during …

    umn Repository record for Synthesized speech intelligibility and preschool age children: comparing accuracy for single word repetition with repeated exposure. (opens in a new tab)

  4. The perception of natural, cell phone, and computer -synthesized speech during the performance of simultaneous visual -motor tasks

    … of top-down and bottom-up information on speech perception in complex listening environments. Specifically, the effects of listening to different types of processed speech were examined on intelligibility and on simultaneous visual-motor performance. The goal was to extend the …

    nebraska Repository record for The perception of natural, cell phone, and computer -synthesized speech during the performance of simultaneous visual -motor tasks (opens in a new tab)

  5. Developing a Framework for Metrics and Evaluation of the Impact of Acoustic-Prosodic Features in Synthesized Speech on Listener Perception in Dyadic Interactions

    Acoustic-prosodic properties of conversational speech have been shown in prior research to impact the perceptions that listeners have towards the speakers in dyadic interactions. While correlations between the two have been consistently found, no standardized framework yet exists for systematically …

    washington Repository record for Developing a Framework for Metrics and Evaluation of the Impact of Acoustic-Prosodic Features in Synthesized Speech on Listener Perception in Dyadic Interactions (opens in a new tab)

  6. Assessment of time frequency warping for use as a reference degradation for assessing synthetic speech

    … method for rating and comparing the quality of synthesized speech. This study assesses the suitability of Time Frequency Warping (TFW) modulation for use as a reference device for assessing synthesized speech. Time Frequency Warping modulation introduces timing errors into natural speech that …

    aston Download PDF for Assessment of time frequency warping for use as a reference degradation for assessing synthetic speech (opens in a new tab)

  7. A Comparison of Speech Output Types For a Child With a Developmental Disability

    … study was to analyze the effects the type of speech output has on the communication of an individual with a developmental disability. Current research has shown positive impacts on the language abilities of children using speech generating devices (SGDs). However, little research has addressed …

    mo-state Repository record for A Comparison of Speech Output Types For a Child With a Developmental Disability (opens in a new tab)

  8. Prosody in text-to-speech synthesis using fuzzy logic

    … and researchers have tried to reproduce human speech. Today, the quality of synthesized speech is not equivalent to the quality of real speech. Most research on speech synthesis focuses on improving the quality of the speech produced by Text-to-Speech (TTS) systems. The best TTS systems use …

    wvu Repository record for Prosody in text-to-speech synthesis using fuzzy logic (opens in a new tab)

  9. Lithuanian speech synthesis using neural networks /

    … inputs to solve the pronunciation problem of synthesized speech for higher-degree phonemic orthography languages. Tacotron 2 and VITS neural network architectures were used to train neural networks on multiple Lithuanian language datasets. Three single-speaker Lithuanian language speech …

    vilnius Repository record for Lithuanian speech synthesis using neural networks / (opens in a new tab)

  10. Assessing human performance trade-offs of a telephone-based information system

    … levels each. The four factors manipulated were: synthesized speech rate, time available for user input, subject age, and background music level. Subjects searched a fictitious department store database for 16 specific store items and transcribed 16 information messages which were spoken by a …

    vt Repository record for Assessing human performance trade-offs of a telephone-based information system (opens in a new tab)

  11. A Developmental Study of ASR-Enhanced E-Book Software to Improve on-Task Interaction for First Grade Users

    … design elements investigated include human vs. synthesized audio feedback, segmented vs. whole-word pronunciation, format of supporting graphic (image vs. animation), use of automatic speech recognition (ASR) to encourage or enforce oral reading of an e-book, and effect of tutorial with …

    boise Repository record for A Developmental Study of ASR-Enhanced E-Book Software to Improve on-Task Interaction for First Grade Users (opens in a new tab)

  12. Transformer-Based lithuanian text stressing for speech synthesis /

    … stress prediction into Lithuanian text-to-speech (TTS) systems by developing and evaluating a Transformer-based model for assigning stress marks in written text. Lithuanian is a stress-sensitive and morphologically rich language where stress is typically omitted in writing and must be …

    vilnius Repository record for Transformer-Based lithuanian text stressing for speech synthesis / (opens in a new tab)

  13. Modeling and Generating Trustworthy Speech

    … advances in natural language generation and speech synthesis have significantly improved fluency and intelligibility, most systems are not designed to control how trustworthy they are perceived. As a result, a mismatch can emerge between perceived trustworthiness and actual system capability, …

    cuny-grad Repository record for Modeling and Generating Trustworthy Speech (opens in a new tab)

  14. An Evaluation of a Talking Machine: the HC 120 Phonic Mirror Handivoice

    … sought to determine the basic intelligibility of synthesized speech as produced by the HC 120 Phonic Mirror Handivoice. It involved 48 male and female subjects divided into two groups. Group 1 had 40 subjects ranging in age from 18 to 44 years. Group 2 had eight subjects ranging in age from 18 to …

    portland-state Repository record for An Evaluation of a Talking Machine: the HC 120 Phonic Mirror Handivoice (opens in a new tab)

  15. Advancing Deep-Generated Speech and Defending against Its Misuse

    <p>Deep learning has revolutionized speech generation, spanning synthesis areas such as text-to-speech and voice conversion, leading to diverse advancements. On the one hand, when trained on high-quality datasets, artificial voices now exhibit a level of synthesized quality that rivals human speech …

    duke Repository record for Advancing Deep-Generated Speech and Defending against Its Misuse (opens in a new tab)

  16. Investigating Pilot Performance Using Mixed-Modality Simulated Data Link

    … to compare the intelligibility of two text-to-speech (TTS) engines (DECtalk and AT&T's Natural Voices) as presented in 85 dB(A) aircraft cockpit engine noise. Results indicated significant differences in intelligibility (p £ 0.05) between the two speech synthesizers across the tested …

    vt Repository record for Investigating Pilot Performance Using Mixed-Modality Simulated Data Link (opens in a new tab)

  17. Block Encoding of Speech Spectral Principal Components

    … series expansion was used to block encode speech spectral principal components as a function of time. Each of ten principal components was first obtained as a linear combination of 2© speech spectral band energies. Using a fixed block length of 10 frames (0.128 s), the K-L basis vectors …

    odu Repository record for Block Encoding of Speech Spectral Principal Components (opens in a new tab)

  18. The establishment of a speech output communication system for a non-verbal child with severe behavioural and cognitive disabilities

    … how Mary learned to use symbols combined with speech output to request food in a natural setting, and in the absence of suggested communication intervention pre-requisites. Data were collected during forty-three sessions, each 15 minutes long. Verbal and physical prompts were used to teach Mary …

    ubc Repository record for The establishment of a speech output communication system for a non-verbal child with severe behavioural and cognitive disabilities (opens in a new tab) Download PDF for The establishment of a speech output communication system for a non-verbal child with severe behavioural and cognitive disabilities (opens in a new tab)

Page 1 of 3