PROSODY-BASED UNIT-SELECTION FOR JAPANESE SPEECH SYNTHESIS

3rd ESCA/COCOSDA Workshop on Speech Synthesis, SSW 1998

Volumn , Issue , 1998, Pages 181-184

  Fujisawa, Ken ^a   Campbell, Nick ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; SIGNAL PROCESSING;

CONCATENATIVE SPEECH SYNTHESIS SYSTEMS; CONCATENATIVE SPEECH SYNTHESIZERS; CORPUS-BASED; JAPANESE SPEECH; SEGMENT SELECTION; SIGNAL-PROCESSING; SUBJECTIVE EXPERIMENTS; UNIT SELECTION; VOICE CHARACTERISTICS; WAVEFORMS;

SPEECH SYNTHESIS;

EID: 85009152072     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. N. Campbell. CHATR: A High-Definition Speech Re-Sequencing System. In Proc. 3rd ASA/ASJ Joint Meeting, pp. 1223-1228, Dec 1996.
2. A. Black and N. Campbell. Optimising selection of units from speech databases for concatenative synthesis. In Proc. Eurospeech95, pp. 581-584, Apr. 1995..
3. K. Fujisawa, T. Hirai, and N. Higuchi. Use of pitch pattern improvement in the CHATR speech speech synthesis system. In Proc. EurospeechOl, pp. 2671-2674, Sep. 1997.
4. N. Campbell. Autolabelling Japanese T o B l . In Proc. of ICSLP, pp. 2399-2402, Oct 1996.
5. N. Campbell and J. Venditti. J-ToBl: an intonation labelling system for Japanese. In Proc. Fall Meeting, Acoust. Soc. Jpn., pp. 317-318, Sept. 1995.
6. N. Campbell, Y. Itoh, W. Ding, and N. Higuchi. Factors affecting perceived quality and intelligibility in the CHATR concatenative speech synthesiser. In Proc. Eurospeech 97, pp. 2635-2638, Sep. 1997.