Analysis and Synthesis of Speech: Strategic Research Towards High-Quality Text-To-Speech Generation (Speech Research, Vol 11)

The International Federation of Library Associations and Institutions (IFLA) is the leading international body representing the interests of library and information services and their users. It is the global voice of the information profession. The series IFLA Publications deals with many of the means through which libraries, information centres, and information professionals worldwide can formulate their goals, exert their influence as a group, protect their interests, and find solutions to global problems. List of figures List of tables Preface A five year research program “Analysis and Synthesis of Speech” 1. Input characteristics Text features affecting listening performance in one way speech communication Text Scan: A preprocessing module for automatic text-to-speech conversion 2. Linguistic aspects Multiple paths to the lexicon MORPA: A morpheme lexicon based morphological parser MORPHON: Lexicon-based text-to-phoneme conversion and phonological rules Pattern-driven morphological decomposition Prosodic sentence analysis without parsing Prosodic analysis: The next generation 3. Building blocks for speech synthesis Speech synthesis with accented and unaccented diphones Development of rule based analysis for text-to-speech 4. Acoustic-phonetic data and synthesis rules How does speaking rate influence vowel formant track parameters? From data to rules: A background survey Collecting data for a speech database 5. Prosody Accentuation, information value and word duration: Effects on speech production, naturalness and sentence processing Human and synthetic intonation: A case study Sandhi processes in natural and synthetic speech 6. Signal analysis Speech quality and speaker characteristics Robust ARMA analysis for speech research 7. Implementations and evaluation A stand-alone text-to-speech system Speech Maker: A flexible framework for constructing text-to-speech systems Evaluation of text-to-speech conversion for Dutch Appendix 1. Institutes and individuals participating in ASSP Appendix 2. Publications by SPIN-funded researchers References Name index Subject index This volume is intended to give colleagues in the field of speech technology an overall idea of the work involved in the research program Analysis and Synthesis of Speech (ASSP).