Acoustic model adaptation based on pronunciation variability analysis for non-native speech recognition

Speech Communication

Volumn 49, Issue 1, 2007, Pages 59-70

  Oh, Yoo Rhee ^a   Yoon, Jae Sam ^a   Kim, Hong Kook ^a  

^a Gwangju Institute of Science and Technology (GIST)   (South Korea)

Author keywords

Acoustic model adaptation; Data driven pronunciation variability; Decision tree; Knowledge based pronunciation variability; Non native speech; Speech recognition; State clustering; State tying

Indexed keywords

ACOUSTIC PROPERTIES; DATA STORAGE EQUIPMENT; DECISION THEORY; KNOWLEDGE BASED SYSTEMS; MATHEMATICAL MODELS; SPEECH ANALYSIS;

ACOUSTIC MODEL ADAPTATION; DATA-DRIVEN PRONUNCIATION VARIABILITY; DECISION TREE; KNOWLEDGE-BASED PRONUNCIATION VARIABILITY; NON-NATIVE SPEECH; STATE-CLUSTERING; STATE-TYING;

SPEECH RECOGNITION;

EID: 33845875676     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2006.10.006     Document Type: Article

References (19)

1. Binder, N., Gruhn, R., Nakamura, S., 2002. Recognition of non-native speech using dynamic phoneme lattice processing. In: Proc. Spring Meeting of the Acoustical Society of Japan, Yokohama, Japan, pp. 203-204.
2. Compernolle D.V. Recognizing speech of goats, wolves, sheep and ... non-natives. Speech Comm. 35 (2001) 71-79
3. Gruhn, R., Markov, K., Nakamura, S., 2004. A statistical lexicon for non-native speech recognition. In: Proc. ICSLP, Jeju Island, Korea, pp. 1497-1500.
4. Leggetter C.J., and Woodland P.C. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. 9 2 (1995) 171-185
5. Matsunaga, S., Ogawa, A., Yamaguchi, Y., Imamura, A., 2003. Non-native English speech recognition using bilingual English lexicon and acoustic models. In: Proc. ICASSP, Hong Kong, China, pp. 340-343.
6. Morgan, J., 2004. Making a speech recognizer tolerate non-native speech through Gaussian mixture merging. In: Proc. InSTIL/ICALL Symposium on Computer-Assisted Language Learning, Venice, Italy, pp. 213-216.
7. Paul, D., Baker, J., 1992. The design for the Wall Street Journal-based CSR corpus. In: Proc. DARPA Speech and Language Workshop, Arden House, NY, pp. 357-362.
8. Rhee, S.-C., Lee, S.-H., Kang, S.-K., Lee, Y.-J., 2004. Design and construction of Korean-Spoken English Corpus (K-SEC). In: Proc. ICSLP, Jeju Island, Korea, pp. 2769-2772.
9. Ryu S.Y. A comparison of English and Korean for teaching English consonants in the Korea KSL class. Jungang J. English Literature Linguist. 35 (1994) 145-160
10. Steidl, S., Stemmer, G., Hacker, C., Noth, E., 2004. Adaptation in the pronunciation space for non-native speech recognition. In: Proc. ICSLP, Jeju Island, Korea, pp. 2901-2904.
11. Strik H., and Cucchiarini C. Modeling pronunciation variation for ASR: a survey of the literature. Speech Comm. 29 (1999) 225-246
12. Tomokiyo, L.M., 2000. Lexical and acoustic modeling of non-native speech in LVCSR. In: Proc. ICSLP, Beijing, China, pp. 346-349.
13. Wang, Z., Schultz, T., 2003. Non-native spontaneous speech recognition through polyphone decision tree specialization. In: Proc. EUROSPEECH, Geneva, Switzerland, pp. 1449-1452.
14. Weide, H., 1998. The CMU Pronunciation Dictionary, release 0.6, Carnegie Mellon University.
15. Youe H.-M. A survey of the Korean learners' problems in mastering English pronunciation. Malsori 42 (2001) 47-56
16. Young, S. et al., 2002. The HTK Book (for HTK Version 3.2), Microsoft Corporation, Cambridge University Engineering Department.
17. Young, S., Odell, J., Woodland, P., 1994. Tree-based state tying for high accuracy acoustic modeling. In: Proc. ARPA Human Language Technology Workshop, Princeton, NJ, pp. 307-312.
18. Yun H.S. An analysis of English vowels in the middle school textbooks: in comparison with the Korean vowels. J. English Lang. Literature 47 2 (2005) 307-328
19. Zavagliakos, G., Schwartz, R., McDonough, J., 1996. Maximum a posteriori adaptation for large scale HMM recognizers. In: Proc. ICASSP, Atlanta, GA, pp. 725-728.