Achieving a reliable compact acoustic model for embedded speech recognition system with high confusion frequency model handling

Speech Communication

Volumn 48, Issue 6, 2006, Pages 737-745

  Park, Junho ^a   Ko, Hanseok ^a  

^a Korea University   (South Korea)

Author keywords

Compact acoustic modeling; Embedded speech recognition system; Tied mixture HMM

Indexed keywords

EMBEDDED SYSTEMS; MATHEMATICAL MODELS; OPTIMIZATION; PROBLEM SOLVING; RESOURCE ALLOCATION; SPEECH RECOGNITION;

COMPACT ACOUSTIC MODELING; EMBEDDED SPEECH RECOGNITION SYSTEM; STATE-CLUSTERED TIED-MIXTURE (SCTM); TIED-MIXTURE HMM;

ACOUSTICS;

EID: 33646259972     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2005.10.001     Document Type: Article

References (18)

1. Bocchieri E., and Mak B.K.-W. Subspace distribution clustering hidden Markov model. IEEE Trans. Speech Audio Process. 9 March (2001) 264-276
2. Boll S.F. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust. Speech Signal Process. 27 2 (1979) 113-120
3. D'Orta, P., Ferretti, M., Scarci, S., 1987. Phoneme classification for real time speech recognition of Italian. In: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, pp. 81-84.
4. Duchateau J., Demyunck K., and Van Compernolle D. Fast and accurate acoustic modeling with semi-continuous HMMs. Speech Comm. 24 (1998) 5-17
5. Gales M., Knill K., and Young S. State-based Gaussian selection in large vocabulary continuous speech recognition using HMM's. IEEE Trans. Speech Audio Process. 7 March (1999) 152-161
6. Huang, X., Jack, M., 1998. Semi-continuous hidden Markov models with maximum likelihood VQ. In: IEEE Workshop on Speech Recognition, New York.
7. Huang, X., Hwang, M.Y., Mahajan, M., 1996. Deleted interpolation and density sharing for continuous hidden Markov models. In: ICASSP'96, Vol. 2, pp. 885-888.
8. Hwang M.Y., and Huang X. Shared-distribution hidden Markov models for speech recognition. IEEE Trans. Speech Audio Process. 1 4 (1993) 414-420
9. Jelinek F. Statistical Methods for Speech Recognition (1997), MIT Press, Cambridge, MA
10. Juang B., and Rabiner L. A probabilistic distance measure for hidden Markov models. Bell System Tech. J. 64 (1985) 391-408
11. Juang B.H., Chou W., and Lee C.H. Minimum classification error rate methods for speech recognition. IEEE Trans. Speech Audio Process. 5 3 (1997) 257-265
12. Kim N., and Un C. Statistically reliable deleted interpolation. IEEE Trans. Speech Audio Process. 5 May (1997) 292-295
13. Kim, K., Ko, H., 2004. Tied mixture modeling optimization for Korean-digit in the embedded ASR system. In: 8th IEEE Internat. Sympos. on Consumer Electronics, pp. 595-599.
14. Lee, A., Kawahara, T., Takeda, K., Shikano, K., 2000. A new phonetic tied-mixture model for efficient decoding. In: ICASSP'2000, Vol. 3, pp. 1269-1272.
15. Moreno P.J., Raj B., and Stern R.M. Data-driven environmental compensation for speech recognition: A unified approach. Speech Comm. 24 4 (1998) 267-285
16. Park, J., Ko, H., 2004. Compact acoustic model for embedded implementation. In: ICSLP'2004, Vol. 1, pp. 693-696.
17. Park J., and Ko H. Effective acoustic model clustering via decision-tree with supervised learning. Speech Comm. 46 1 (2005) 1-13
18. Young, S., 1992. The general use of tying in phoneme-based HMM speech recognizers. In: ICASSP'92, Vol. 1, pp. 569-572.