Fundamentals of Speech Synthesis and Speech Recognition
Explains and discusses how human speakers and listeners process speech and language. Focuses on those elements of current research which have the most bearing on future developments in the production of truly natural-sounding speech and the reliable recognition of continuous speech. Presents a concise and clear introduction to this increasingly complex and interdisciplinary field.
Search in google:
Explains and discusses how human speakers and listeners process speech and language. Focuses on those elements of current research which have the most bearing on future developments in the production of truly natural-sounding speech and the reliable recognition of continuous speech. Presents a concise and clear introduction to this increasingly complex and interdisciplinary field. Booknews Arguing that further progress in getting computers to speak convincingly and to understand human speech depends on exploiting and stimulating complex knowledge about how human speakers and listeners process speech and language, presents the essential elements of current research in those fields most likely to contribute to such progress. Also covers the relevant developments in speech signal processing, statistical modelling, and artificial neural network architecture. For graduate students and advanced undergraduates in computer science, engineering, linguistics, and psychology, and armchair tourists from neighboring disciplines. Annotation c. Book News, Inc., Portland, OR (booknews.com)
Preface1Fundamentals of Phonetic Science52Prosodic Aspects of Speech233Pauses and the Temporal Structure of Speech414Subphonemic Segment Inventories for Concatenative Speech Synthesis695Text-to-Speech Synthesis: An Introduction and A Case Study876Format Synthesis1097Automatic Speech and Speaker Recognition: Overview, Current Issues and Perspectives1298Stochastic Models and Artificial Neural Networks for Automatic Speech Recognition1499The Prediction of Vowel Systems: Perceptual Contrast and Stability18510Articulatory Models in Speech Synthesis21511Dynamic Modelling and Control of Speech Articulators: Application to Vowel Reduction23112Phonological Structure, Parametric Phonetic Interpretation and Natural-Sounding Synthesis25313Semantic and Pragmatic Prediction of Prosodic Structures27114Separating Simultaneous Sound Sources: Issues, Challenges and Models29715Auditory Computations that Separate Speech from Competing Sounds: A Comparison of Monaural and Binaural Processes31316Multimodal Human-Computer Interface339Index375
\ BooknewsArguing that further progress in getting computers to speak convincingly and to understand human speech depends on exploiting and stimulating complex knowledge about how human speakers and listeners process speech and language, presents the essential elements of current research in those fields most likely to contribute to such progress. Also covers the relevant developments in speech signal processing, statistical modelling, and artificial neural network architecture. For graduate students and advanced undergraduates in computer science, engineering, linguistics, and psychology, and armchair tourists from neighboring disciplines. Annotation c. Book News, Inc., Portland, OR (booknews.com)\ \
