TEXT-TO-SPEECH CONVERSION WITH NEURAL NETWORKS: A RECURRENT TDNN APPROACH

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

Volumn , Issue , 1997, Pages 561-564

  Karaali, O ^a   Corrigan, G ^a   Gerson, I ^a   Massey, N ^a  

^a MOTOROLA INC   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

NETWORK ARCHITECTURE; SPEECH COMMUNICATION; SPEECH SYNTHESIS;

ACOUSTIC MAPPING; DATA INPUT; NEURAL NETWORK ARCHITECTURE; NEURAL-NETWORKS; OUTPUT PARAMETERS; SPEECH SYNTHESIS SYSTEM; TEXT-TO-SPEECH CONVERSION; TEXT-TO-SPEECH SYSTEM; TIME DOMAIN; VOICE QUALITY;

RECURRENT NEURAL NETWORKS;

EID: 85122382944     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. J. Burniston and K. M. Curtis "A Hybrid Neural Network/Rule Based Architecture for Diphone Speech Synthesis", Proc. International Symposium on Speech, Image Processing, and Neural Networks, pp. 323-326, Hong Kong, April 1994.
2. G. C. Cawley and P. D. Noakes, "LSP Speech Synthesis Using Backpropagation Networks", Proc. Third International Conference on Artificial Neural Networks, pp. 291-294, Brighton, May 1993.
3. A. J. Cohen and M. J. Bishop, "Self-organizing Maps in Synthetic Speech", Proc. WCNN '94, San Diego, Junk 1994.
4. C. Tuerk and T. Robinson, "Speech Synthesis using Artificial Neural Networks Trained on Cepstral Coefficients", Proc. Eurospeech '93, pp. 1713-1716, Berlin, September 1993.
5. T. Weijters and J. Thole, "Speech Synthesis with Artificial Neural Networks", Proc. ICNN '93 pp. 1764-1769, San Francisco, March 1993.
6. G. Corrigan, N. Massey, and O. Karaali, "Generating Segment Durations in a Text-to-speech system: A Hybrid Rule-based/Neural Network Approach", Proc. Eurospeech '97, Rhodes, September 1997.
7. J. Makhoul, R. Viswanathan, R. Schwartz, and A. W. F. Huggins, "A Mixed-Source Model for Excitation and Synthesis", Proc. ICASSP '78, pp. 163-166, Tulsa, April 1978.
8. H. Nusbaum, A Francis, and T. Luks, "Comparative Evaluation of the Quality of Synthetic Speech Produced at Motorola", Technical Report 1, University of Chicago, 1995.