Automatic generation of synthesis units and prosodic information for Chinese concatenative synthesis

Speech Communication

Volumn 35, Issue 3-4, 2001, Pages 219-237

  Wu, Chung Hsien ^a   Chen, Jau Hung ^a  

^a NATIONAL CHENG KUNG UNIVERSITY   (Taiwan)

Author keywords

Chinese text to speech conversion; Concatenative synthesis; Pitch contour; Prosodic information; Syllable duration; Synthesis units

Indexed keywords

DATABASE SYSTEMS; DISTORTION (WAVES); LINGUISTICS;

CONCATENATIVE SYNTHESIS; PROSODIC INFORMATIONS;

SPEECH SYNTHESIS;

EID: 0035478985     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(00)00075-3     Document Type: Article

References (17)

1. Multilingual PSOLA text-to-speech system
2. Prosodic rules for connected Mandarin synthesis
3. Diphone synthesis using an overlap-add technique for speech waveforms concatenation
4. Vector quantization of pitch information in Mandarin speech
5. An RNN-based prosodic information synthesizer for Mandarin text-to-speech
6. Corpus-based Mandarin speech synthesis with contextual syllabic units based on phonetic properties
7. Speech analysis/synthesis and modification using an analysis-by-synthesis/overlap-add sinusoidal modal
8. Development of a text-to-speech for Japanese based on waveform splicing
9. Review of text-to-speech conversion for English
10. The synthesis rules in a Chinese text-to-speech system
11. Improved tone concatenation rules in a formant-based Chinese text-to-speech system
12. Shape invariant time-scale and pitch modification of speech
13. Neural network based generation of fundamental frequency contours
14. Issues in text-to-speech conversion for Mandarin
15. A hierarchical neural network model based on a C/V segmentation algorithm for isolated Mandarin speech recognition
16. A novel two-level method for the computation of the LSP frequencies using a decimation-in-degree algorithm