Between-word distance calculation in a symbolic domain and its applications to speech recognition

Information sciences

Volumn 123, Issue 1, 2000, Pages 25-41

  Tanaka, Kazuyo ^a   Kojima, Hiroaki ^a  

^a ELECTROTECHNICAL LABORATORY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

DYNAMIC PROGRAMMING; ESTIMATION; MARKOV PROCESSES; MATHEMATICAL MODELS; SPEECH ANALYSIS; STATISTICAL METHODS; WORD PROCESSING;

BETWEEN-WORD DISTANCE (BWD) CALCULATIONS; HIDDEN MARKOV MODEL (HMM); SUBPHONEMIC SEGMENT SEQUENCES;

SPEECH RECOGNITION;

EID: 0033900204     PISSN: 00200255     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0020-0255(99)00108-5     Document Type: Article

References (21)

1. Jelinek F. Statistical Method for Speech Recognition. 1997;MIT Press, Cambridge, MA.
2. Bahl L.R., Jelinek F. Decoding for channels with insertions deletions and substitutions with application to speech recognition. IEEE Trans. Inform. Theory. IT-21:1975;404-411.
3. Otsuki T., Ito A., Makino S., Sone T. Performance prediction of word recognition using transition information between phonemes or between characters (in Japanese). Institute of Electronics, Information and Communication Engineers, Japan (IEICEJ) Trans. J76-D-II. J76:1993;1090-1096.
4. Nakagawa S. Relationship between phoneme recognition performance and word recognition rate (in Japanese). J. Inform. Soc. Japan. 22(3):1981;488-496.
5. Nakagawa S., Ooguro Y., Murase I. An evaluation method for continuous speech recognition systems (in Japanese). IEICE Trans. J73-D-II. 73(2):1990;683-693.
6. K. Tanaka, S. Hayamizu, K. Ohta, A demiphoneme network representation of speech and automatic labeling techniques of speech database construction, Proc. IEEE ICASSP-86, Paper 7.1, 1986.
7. Tanaka K., Hayamizu S., Ohta K. Automatic labeling of known speech using a demiphoneme network representation and a parameter series segmentation in Japanese. J. Acoust. Soc. Japan. 42(11):1986;860-868.
8. K. Tanaka, S. Hayamizu, K.Ohta, Sorting and clustering of acoustic-phonetic variations based on a fine-labeled speech database with applications for automatic word recognition (in Japanese), IEICEJ Trans. J73-D-II 73 J73 (1990) 1619-1629.
9. Hayamizu S., Tanaka K., Yokoyama S., Ohta K. Generation of VCV/CVC balanced word sets for speech database in Japanese. Bull. Electrotech. Lab. 40(10):1985;803-834.
10. Spaeth H. Cluster Analysis Algorithm. 1980;Ellis Horwood, Chichester, UK.
11. Young S. The HTK Book. 1996;Entropic Cambridge Research Lab, Cambridge.
12. M.M. Sondhi, S.E. Levinson, Computing relative redundancy to measure grammatical constraint in speech recognition tasks, in: Proc. IEEE ICASSP-78, 1978, pp. 409-412.
13. L.R. Bahl, J.K. Baker et. al., Automatic Recognition of continuously spoken sentences from a finite state grammar, in: Proc. IEEE ICASSP-78, 1978, pp. 418-421.
14. A. Asadi, R. Schwarz, J. Makhoul, Automatic detection of new words in a large vocabulary continuous speech, in: Proc. ICASSP-90, 1990, pp.125-128.
15. T. Watanabe, S. Tsukada, Unknown utterance rejection using likelihood normarization based on syllable recognition (in Japanese), IEICEJ Trans. J75-D-II J75 (1992) pp. 2002-2009.
16. Hayamizu S., Itou K., Tanaka K. Detection of unknown words in large vocabulary speech recognition. J. Acoust. Soc. Japan E. 16(3):1995;165-171.
17. K. Tanaka, H. Kojima, A method of extracting time-varying acoustic features effective for speech recognition, in: Proc. IEEE ICASSP-97, 1997, pp. 1391-1394.
18. S. Hayamizu, K.Tanaka, K.Ohta, A large vocabulary word recognition system using rule-based network representation of acoustic characteistic variations, in: Proc. IEEE ICASSP-88, 1988-4, pp. 211-214.
19. Ostendorf M., Digalakis V.V., Kimball O.A. From HMM's to segment models: a unified view of stochastic modeling for speech recognition. IEEE Trans. Speech Audio Processing. 4:1996;360-378.
20. Foote J.T., Young S.J., Jones G.J.F., Jones K.S. Unconstrained keyword spotting using phone lattices with application to spoken document retrieval. Computer Speech and Language. 11:1997;207-224.
21. D. Albesano, R. Gemello, F. Mana, Hybrid HHM-NN modeling of stationary-transitional units for continuous speech recognition, in: Proc. ICONIP-97, 1997, pp. 1112-1115.