Developments in Speech Synthesis

Introduction.

Part I: Current Work.

1. High-Level and Low-Level Synthesis.

2. Low-Level Synthesisers: Current Status.

3. Text-To-Speech.

4. Different Low-Level Synthesisers: What Can Be Expected?

5. Low-Level Synthesis Potential.

Part II: A New Direction for Speech Synthesis.

6. A View of Naturalness.

7. Physical Parameters and Abstract Information Channels.

8. Variability and System Integrity.

9. Automatic Speech Recognition.

Part III: High-Level Control.

10. The Need for High-Level Control.

11. The Input to High-Level Control.

12. Problems for Automatic Text Markup.

Part IV: Areas for Improvement.

13. Filling Gaps.

14. Using Different Units.

15. Waveform Concatenation Systems: Naturalness and Large Databases.

16. Unit Selection Systems.

Part V: Markup.

17. VoiceXML.

18. Speech Synthesis Markup Language (SSML).

19. SABLE.

20. The Need for Prosodic Markup.

Part VI: Strengthening the High-Level Model.

21. Speech.

22. Basic Concepts.

23. Underlying Basic Disciplines: Expression Studies.

24. Labelling Expressive/Emotive Content.

25. The Proposed Model.

26. Types of Model.

Part VII: Expanded Static and Dynamic Modelling.

27. The Underlying Linguistics System.

28. Planes for Synthesis.

Part VIII: The Prosodic Framework, Coding and Intonation.

29. The Phonological Prosodic Framework.

30. Sample Code.

31. XML Coding.

32. Prosody: General.

33. Phonological and Phonetic Models of Intonation.

Part IX: Approaches to Natural-Sounding Synthesis.

34. The General Approach.

35. The Expression Wrapper in XML.

36. Advantages of XML in Wrapping.

37. Considerations in Characterising Expression/Emotion.

38. Summary.

Part X: Concluding Overview.

References.

Author Index.

Index.