Phoneme boundary estimation using bidirectional recurrent neural networks and its applications

Systems and Computers in Japan

Volumn 30, Issue 4, 1999, Pages 20-30

  Fukada, Toshiaki ^a,b,c,d,e   Schuster, Mike ^a   Sagisaka, Yoshinori ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^c Canon Media Technology Laboratories

^d CARNEGIE MELLON UNIVERSITY   (United States)

^e Inst Electronics Info Commun E   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

BIDIRECTIONAL RECURRENT NEURAL NETWORKS; PHONEME BOUNDARY ESTIMATIONS; SEGMENT MODELS;

BOUNDARY CONDITIONS; COMPUTATIONAL COMPLEXITY; MARKOV PROCESSES; MATHEMATICAL MODELS; MULTILAYER NEURAL NETWORKS; PARAMETER ESTIMATION; RECURRENT NEURAL NETWORKS;

SPEECH RECOGNITION;

EID: 0033116017     PISSN: 08821666     EISSN: None     Source Type: Journal    
DOI: 10.1002/(SICI)1520-684X(199904)30:4<20::AID-SCJ3>3.0.CO;2-E     Document Type: Article

References (22)

1. Woodland P, Leggetter C, Odell J, Valtchev V, Young S. The 1994 HTK large vocabulary speech recognition system. Proc ICASSP-95:73-76.
2. Shimizu T, Yamamoto H, Masataki H, Matsunaga S, Sagisaka Y. Spontaneous dialogue speech recognition using cross-word context constrained word graphs. Proc ICASSP-96:145-148.
3. Sagisaka Y, Campbell N, Higuchi N. Computing PROSODY: Computational models for processing spontaneous speech. Springer: 1997.
4. Kompe R, Kießling A, Niemann H, Nöth E, Batliner A, Schachtl S, Ruland T, Block H. Improving parsing of spontaneous speech with the help of prosodic boundaries. Proc ICASSP-97:811-814.
5. Reichl W, Ruske G. Syllable segmentation of continuous speech with artificial neural networks. Proc Eurospeech-93:1771-1774.
6. Leung H, Glass J, Phillips M, Zue V. Detection and classification of phonemes using context-independent error back-propagation. Proc ICSLP-90:1061-1064.
7. Austin S, Zavaliagkos G, Makhoul J, Schwartz R. Speech recognition using segmental neural nets. Proc ICASSP-92:I-625-I-628.
8. Svendsen T, Soong FK. On the automatic segmentation of speech signals. Proc ICASSP-87:77-80.
9. Ljolje A, Riley M. Automatic segmentation and labeling of speech. Proc ICASSP-91:473-476.
10. Glass J, Chang J, McCandless M. A probabilistic framework for feature-based speech recognition. Proc ICSLP-96:2277-2280.
11. Wu S-L, Shire M, Greenberg S, Morgan N. Integrating syllable boundary information into speech recognition. Proc ICASSP-97:987-990.
12. Verhasselt J, Illina I, Martens J-P, Gong Y, Haton J-P. The importance of segmentation probability in segment based speech recognizers. Proc ICASSP-97:1407-1410.
13. Schuster M, Paliwal K. Bidirectional recurrent neural networks. IEEE Trans Signal Process 1997;45:2673-2681.
14. Robinson A. An application of recurrent neural nets to phone probability estimation. IEEE Trans Neural Networks 1994:5(2).
15. Fisher W, Doddington G, Goudie-Marshall K. The DARPA speech recognition research database: Specifications and status. Proc DARPA Workshop on Speech Recognition. Feb 1986:93-99.
16. Riedmiller M, Braun H. A direct adaptive method for faster back-propagation learning: The RPROP algorithm. Proc IEEE Int Conf Neural Networks 1993: 586-591.
17. Takami J, Sagayama S. A successive state splitting algorithm for efficient allophone modeling. Proc ICASSP-92:573-576.
18. Robinson T. Several improvements to a recurrent error propagation network phone recognition system. Cambridge University Engineering Department Tech Rep CUED/F-INFENG/TR82, 1991.
19. Ostendorf M, Digalakis V, Kimball O. From HMM's to segment models: A unified view of stochastic modeling for speech recognition. IEEE Trans Speech Audio Process 1996;4:370-378.
20. Gish H, Ng K. A segmental speech model with applications to word spotting. Proc ICASSP-93:II-447-II-450.
21. Kannan A, Ostendorf M. A comparison of constrained trajectory models for large vocabulary speech recognition. Boston University Electrical and Computer Engineering Tech Rep ECE-96-007, 1996.
22. Fukada T, Sagisaka Y, Paliwal KK. Model parameter estimation for mixture density stochastic segment models. Proc ICASSP-97:1403-1406.