On the Global FO Shape Model using a Transition Network for Japanese Text-to-Speech Systems

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 2679-2682

  Ishikawa, Yasushi ^a   Ebihara, Takashi ^a  

^a MITSUBISHI ELECTRIC CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION; SPEECH PROCESSING; SYNTACTICS;

CONTROL METHODS; FUNDAMENTAL FREQUENCY CONTROL; GLOBAL MODELS; JAPANESE TEXT; LOCAL MODEL; PITCH MODELING; SHAPE MODELLING; SYNTACTIC ANALYSIS; TEXT-TO-SPEECH SYSTEM; TWO STAGE MODEL;

FORECASTING;

EID: 33646656615     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. M. Abe and H. Sato, "Two-Stage FO Control Model using Syllable based FO Units," ICASSP'92 pp.II-53 - II-56, 1992
2. H. Fujisaki and K. Hirose, "Analysis of voice fundamental frequency contours for declarative sentences of Japanese," J. Acoust. Soc. Jpn(E), 5, pp.233-242 1984
3. Sagisaka,Y. "On the Prediction of Global FO shape for Japanese Text-to-Speech", Proc. ICASSP90 pp.235-328, 1990
4. Traber C. "FO Generation with a database of Natural FO Patterns and with a Neural network:, Proc. ESC A Speech Synthesis Workshop pp. 141-144, 1990
5. TakamiJ. and Sagayama,S., "A Successive State Splitting Algorithm for Efficient Allophone Modeling", ICAASP'92, pp.573-576 (1992)