Recent years have seen the appearance of increasingly powerful text-to-speech and automatic speech recognition devices. However, the production of truly natural-sounding speech still poses considerable problems, and the reliable recognition of continuous speech is still open to major improvements. This text captures the essential elements of current research which have a bearing on future developments, exploiting and simulating complex knowledge about how human speakers and listeners process speech and language.
Partial table of contents:
Fundamentals of Phonetic Science (E. Keller).
Prosodic Aspects of Speech (S. Werner & E. Keller).
Pauses and the Temporal Structure of Speech (B. Zellner).
STATE OF THE ART (E. Keller & J. Caelen).
Text-to-Speech Synthesis: An Introduction and a Case Study (B. Pfister & C. Traber).
Formant Synthesis (T. Styger & E. Keller).
CHALLENGES (E. Keller & J. Caelen).
The Prediction of Vowel Systems: Perceptual Contrast and Stability (L.-J.
Boe, et al.).
Semantic and Pragmatic Prediction of Prosodic Structures (G. Caelen-Haumont).
Multimodal Human-Computer Interface (J. Caelen).
Number Of Pages: 394
Published: 20th October 1994
Country of Publication: GB
Dimensions (cm): 25.15 x 17.3
Weight (kg): 0.82
Edition Number: 1