| Autore |
Tatham Mark
|
| Pubbl/distr/stampa |
Chichester, West Sussex, England ; ; Hoboken, NJ, : J. Wiley, c2005
|
| Descrizione fisica |
1 online resource [358 pages]
|
| Disciplina |
006.5/4
|
| Altri autori (Persone) |
MortonKatherine
|
| Soggetto topico |
Speech processing systems
|
| ISBN |
9786610241705
9781280241703
1280241705
9780470012604
0470012609
9780470012598
0470012595
|
| Formato |
Materiale a stampa  |
| Livello bibliografico |
Monografia |
| Lingua di pubblicazione |
eng
|
| Nota di contenuto |
DEVELOPMENTS IN SPEECH SYNTHESIS; Contents; Acknowledgements; Introduction; How Good is Synthetic Speech?; Improvements Beyond Intelligibility; Continuous Adaptation; Data Structure Characterisation; Shared Input Properties; Intelligibility: Some Beliefs and Some Myths; Naturalness; Variability; The Introduction of Style; Expressive Content; Final Introductory Remarks; Part I Current Work; 1 High-Level and Low-Level Synthesis; 1.1 Differentiating Between Low-Level and High-Level Synthesis; 1.2 Two Types of Text; 1.3 The Context of High-Level Synthesis; 1.4 Textual Rendering; 2 Low-Level Synthesisers: Current Status2.1 The Range of Low-Level Synthesisers Available; 2.1.1 Articulatory Synthesis; 2.1.2 Formant Synthesis; 2.1.3 Concatenative Synthesis; Units for Concatenative Synthesis; Representation of Speech in the Database; Unit Selection Systems: the Data-Driven Approach; Unit Joining; Cost Evaluation in Unit Selection Systems; Prosody and Concatenative Systems; Prosody Implementation in Unit Concatenation Systems; 2.1.4 Hybrid System Approaches to Speech Synthesis; 3 Text-To-Speech; 3.1 Methods; 3.2 The Syntactic Parse; 4 Different Low-Level Synthesisers: What Can Be Expected?4.1 The Competing Types; 4.2 The Theoretical Limits; 4.3 Upcoming Approaches; 5 Low-Level Synthesis Potential; 5.1 The Input to Low-Level Synthesis; 5.2 Text Marking; 5.2.1 Unmarked Text; 5.2.2 Marked Text: the Basics; 5.2.3 Waveforms and Segment Boundaries; 5.2.4 Marking Boundaries on Waveforms: the Alignment Problem; 5.2.5 Labelling the Database: Segments; 5.2.6 Labelling the Database: Endpointing and Alignment; Part II A New Direction for Speech Synthesis; 6 A View of Naturalness; 6.1 The Naturalness Concept; 6.2 Switchable Databases for Concatenative Synthesis6.3 Prosodic Modifications; 7 Physical Parameters and Abstract Information Channels; 7.1 Limitations in the Theory and Scope of Speech Synthesis; 7.1.1 Distinguishing Between Physical and Cognitive Processes; 7.1.2 Relationship Between Physical and Cognitive Objects; 7.1.3 Implications; 7.2 Intonation Contours from the Original Database; 7.3 Boundaries in Intonation; 8 Variability and System Integrity; 8.1 Accent Variation; 8.2 Voicing; 8.3 The Festival System; 8.4 Syllable Duration; 8.5 Changes of Approach in Speech Synthesis; 9 Automatic Speech Recognition9.1 Advantages of the Statistical Approach; 9.2 Disadvantages of the Statistical Approach; 9.3 Unit Selection Synthesis Compared with Automatic Speech Recognition; Part III High-Level Control; 10 The Need for High-Level Control; 10.1 What is High-Level Control?; 10.2 Generalisation in Linguistics; 10.3 Units in the Signal; 10.4 Achievements of a Separate High-Level Control; 10.5 Advantages of Identifying High-Level Control; 11 The Input to High-Level Control; 11.1 Segmental Linguistic Input; 11.2 The Underlying Linguistics Model; 11.3 Prosody; 11.4 Expression; 12 Problems for Automatic Text Markup
|
| Record Nr. | UNINA-9911019182703321 |
Info
2000 IEEE Workshop on Speech Coding
