Phone mismatch penalty matrices for two-stage keyword spotting via multi-pass phone recognizer

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 202-205

  Han, Chang Woo ^a   Kang, Shin Jae ^a   Lee, Chul Min ^a   Kim, Nam Soo ^a  

^a Seoul National University   (South Korea)

Author keywords

Multi pass phone recognition outputs; Phone mismatch penalty matrices; Two stage keyword spotting

Indexed keywords

CHARACTER RECOGNITION; CONTINUOUS SPEECH RECOGNITION; SPEECH COMMUNICATION; SPEECH RECOGNITION;

COMPARATIVE EXPERIMENTS; ERROR GENERATION; INSERTION AND DELETION ERRORS; KEYWORD SPOTTING; MULTI-PASS; PHONE RECOGNITION; TEXT-MATCHING; TRAINING DATA; MATRIX; MULTI-PASS PHONE RECOGNITION OUTPUT; PHONE MISMATCH PENALTY MATRIX; TWO-STAGE KEYWORD SPOTTING; TWO-STATE;

TELEPHONE SETS;

EID: 79959817020     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. S. Dharanipragada and S. Roukos, "A multistage algorithm for spotting new words in speech," IEEE Trans. Speech, Audio Process., vol. 10, no. 8, pp. 542-550, Nov. 2002.
2. D. A. James and S. J. Young, "A fast lattice-based approach to vocabulary independent wordspotting," Proc. ICASSP, pp. 899-902, Apr. 1997.
3. K. M. Knill and S. J. Young, "Low-cost implementation of open set keyword spotting," Computer Speech and Language, pp. 243-266, Jul. 1999.
4. K. Thambiratnam and S. Sridharan, "Dynamic match phone lattice searches for very fast and accurate keyword spotting," Proc. ICASSP, pp. 465-468, Mar. 2005.
5. L. ten Bosch, A. Hamalainen, O. Scharenborg, and L. Boves, "Acoustic scores and symbolic mismatch penalties in phone lattices," Proc. ICASSP, pp. 437-440, May 2006.
6. K. Audhkhasi and A. Verma, "Keyword search using modified minimum edit distance measure," Proc. ICASSP, pp. 929-932, Apr. 2007.
7. C. W. Han, S. J. Kang, and N. S. Kim, "Estimation of phone mismatch penalty matrices for two-stage keyword spotting," IEICE Trans. Inf. Syst. (submitted in Jan. 2010).
8. L. R. Bahl and F. Jelinek, "Decoding for channels with insertions, deletions, and substitutions with applications to speech recognition," IEEE Trans. Information Theory, vol. IT-21, no. 44, pp. 404-411, Jul. 1975.
9. S. Nakagawa and M. M. Jilan, "Syllable-based connected spoken word recognition by two pass O(n) DP matching and hidden Markov models," Proc. ICASSP, pp. 1117-1120, Apr. 1986. (Pubitemid 17485137)
10. Q. Fu, X. He, and L. Deng, "Phone-discriminating minimum classification error (P-MCE) training for phonetic recognition," IEEE Trans. Speech, Audio Process., vol. 10, no. 8, pp. 542-550, Nov. 2002.
11. F. Sha and L. K. Saul, "Comparison of large margin training to other discriminative methods for phonetic recognition by hidden Markov models," Proc. ICASSP, pp. 313-316, May 2007.
12. SiTEC website. [Online]. Available: http://www.sitec.or.kr/