Recovery from false rejection using statistical partial pattern trees for sentence verification

Speech Communication

Volumn 43, Issue 1-2, 2004, Pages 71-88

  Wu, Chung Hsien ^a   Chen, Yeou Jiunn ^b  

^a NATIONAL CHENG KUNG UNIVERSITY   (Taiwan)

^b INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE   (Taiwan)

Author keywords

Error recovery; False rejection error; Partial pattern tree; Sentence verification

Indexed keywords

ALGORITHMS; COMPUTER SYSTEM RECOVERY; ERROR ANALYSIS; MATHEMATICAL MODELS; SPEECH RECOGNITION; STATISTICAL METHODS; TREES (MATHEMATICS);

FALSE REJECTION ERRORS; PARTIAL PATTER TREE (PPT); SENTENCE VERIFICATIONS; SENTENCE-SCORING ALGORITHMS;

SPEECH COMMUNICATION;

EID: 2942538615     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2004.02.003     Document Type: Article

References (34)

1. Bellegarda, J.R., 1999. Speech recognition experiments using multi-span statistical language models. In: Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Vol. 2, pp. 717-720.
2. Benitez M.C., Rubio A., Garcia P., Torre A. Different confidence measures for word verification in speech recognition. Speech Communication. 32:2000;79-94.
3. Billa, J., Colhurst, T., El-Jaroudi, A., Iyer, R., Ma, K., Matsoukas, S., Quillen, C., Richardson, F., Siu, M., Zavaliagkos, G., Gish, H., 1999. Recent experiments in large vocabulary conversational speech recognition. In: Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Vol. 1, pp. 41-44.
4. Chen S.F., Rosenfeld R. A survey of smoothing techniques for ME models. IEEE Trans. on Speech and Audio Process. 8:2000;37-50.
5. Della Pietra V., Della Pietra V., Lafferty J. Inducing features of random fields. IEEE Trans. Pattern Anal. Machine Intell. 19:1997;380-393.
6. Fukunaga K. Introduction to Statistical Pattern Recognition. 1972;Academic, New York.
7. Gorin, A.L., 1996. Processing of semantic information in fluently spoken language. In: Proc. Internat. Conf. Speech and Language Process., Vol. 2, pp. 1001-1004.
8. Guyon, I., Pereira, F., 1995. Design of a linguistic postprocessor using variable memory length Markov models. In: Proc. 3rd ICDAR, pp. 454-497.
9. Hamaker, J.S., 1999. Towards building a better language model for switchboard: the POS tagging task. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., pp. 579-582.
10. Huang E.F., Wang H.C. An efficient algorithm for syllable hypothesization in continuous Mandarin speech recognition. IEEE Trans. on Speech and Audio Process. 2(3):1994;446-449.
11. Iyer, I., Ostendorf, M., 1997. Transforming out-of-domain estimates to improve in-domain language models. In: Proc. Eur. Conf. Speech Commun. and Technology, Vol. 4, pp. 1975-1978.
12. Iyer R.M., Ostendorf M. Modeling long distance dependence in language: topic mixtures versus dynamic cache models. IEEE Trans. on Speech and Audio Process. 7:1999;30-39.
13. Jelinek F. Statistical Methods for Speech Recognition. 1998;MIT Press, Cambridge, MA.
14. Kamppari, S.O., Hazen, T.J., 2000. Word and phone level acoustic confidence scoring. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 3, pp. 1799-1802.
15. Kellner, A., 1998. Initial language models for spoken dialogue systems. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 1, pp. 185-188.
16. Khudanpur, S., Wu, J., 1999. A maximum entropy language model integrating N-grams and topic dependencies for conversational speech recognition. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 1, pp. 553-556.
17. Kremer, S.C., 1997. Parallel stochastic grammar induction. In: Proc. Internat. Conf. Neural Networks, Vol. 3, pp. 1424-1428.
18. Leeuwen G.F.V.B.V., Nieuwoudt C., Botha E.C. Towards a speech recognition based automatic telephone exchange with an afrikaans conversational interface. IEEE Africon. 1:1999;195-196.
19. Lleida E., Rose R.C. Utterance verification in continuous speech recognition: decoding and training procedures. IEEE Trans. on Speech and Audio Process. 8(2):2000;126-139.
20. Ma, K.W., Zavaliagkos, G., Meteer, M., 1998. Sub-sentence discourse models for conversational speech recognition. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 2, pp. 693-696.
21. Moreau, N., Charlet, D., Jouvet, D., 2000. Confidence measure and incremental adaptation for the rejection of incorrect data. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 3, pp. 1807-1810.
22. Niesler T., Woodland P. Variable-length category N-gram language models. Computer Speech and Language. 21:1999;1-26.
23. O'Boyle, R., Ming, J., McMahon, J., Smith, F.J., 1996. Improving N-gram models by incorporating enhanced distributions. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 1, pp. 168-171.
24. Rahim M.G., Lee C.H., Juang B.H. Discriminative utterance for connected digits recognition. IEEE Trans. on Speech and Audio Process. 5:1997;266-277.
25. Ron, D., Singer, Y., Tishby, N., 1994. The Power of Amnesia, Advances in Neural Information Processing Systems 6. Morgan Kaufmann, CA, pp. 176-183.
26. Rose, R.C., Yao, H., Riccardi, G., Wright, J., 1998. Integration of utterance verification with statistical language modeling and spoken language understanding. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 1, pp. 237-240.
27. Sarukkai R.R., Ballard D.H. Word set probability boosting for improved spontaneous dialog recognition. IEEE Trans. on Speech and Audio Process. 5:1997;438-450.
28. Shu, C.Q., 1998. Selected phoneme rejection grammar for a speech recognition system. In: Proc. Internat. Conf. Signal Process., Vol. 1, pp. 646-649.
29. Siu M., Ostendorf M. Variable N-grams and extensions for conversational speech language modeling. IEEE Trans. on Speech and Audio Process. 8:2000;63-75.
30. Stolcke, A., 1998. Entropy-based pruning of backoff language models. In: Proc. DARPA Broadcast News Transcription and Understanding Workshop, pp. 270-274.
31. Wu C.H., Chen Y.J. Multi-keyword spotting of telephone speech using fuzzy search algorithm and keyword-driven two-level CBMS. Speech Communication. 33:2001;197-212.
32. Wu C.H., Chen Y.J., Yan G.L. Integration of phonetic and prosodic information for robust utterance verification. IEE Proc.: Vision Image and Signal Process. 147:2000;55-61.
33. Yamamoto, H., Sagisaka, Y., 1999. Multi-class composite N-gram based on connection direction. In: Proc. Internat. Conf. Acoust., Speech, and Signal Process., Vol. 1, pp. 533-536.
34. Zue V., Seneff S., Glass J.R., Polifroni J., Pao C., Hazen T.J., Hetherington L. Jupiter: A Telephone-Based Conversational Interface for Weather Information. IEEE Trans. on Speech and Audio. 8(1):2000;85-96.