Developing high performance ASR in the IBM multilingual speech-to-speech translation system

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2008, Pages 5121-5124

  Cui, Xiaodong ^a   Gu, Liang ^a   Xiang, Bing ^a   Zhang, Wei ^a   Gao, Yuqing ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Discriminative training; Large vocabulary spontaneous speech recognition; Multilingual speech translation; Noise robustness; Streaming mode decoding

Indexed keywords

ACOUSTICS; COMPUTATIONAL LINGUISTICS; COMPUTER NETWORKS; DECODING; SIGNAL PROCESSING; TRANSLATION (LANGUAGES);

DISCRIMINATIVE TRAINING; LARGE VOCABULARY SPONTANEOUS SPEECH RECOGNITION; MULTILINGUAL SPEECH TRANSLATION; NOISE ROBUSTNESS; STREAMING MODE DECODING;

SPEECH RECOGNITION;

EID: 51449111520     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518811     Document Type: Conference Paper

References (8)

1. Y. Gao, B. Zhou, L. Gu, R. Sarikaya, H.-K. Kuo, A.-V.I. Rosti, M. Afify, and W. Zhu, "IBM MASTOR: Multilingual automatic speech-to-speech translator," Proc. of ICASSP, pp. 1205-1208, 2006.
2. B. Zhou, D. Dechelotte, and Y. Gao, "Two-way speech-to-speech translation on handheld devices," Proc. of ICSLP, pp. 1637-1640, 2004.
3. L. Gu, Y. Gao, F. Liu, and M. Picheny, "Concept-based speech-to-speech translation using maximum entropy models for statistical natural concept generation," IEEE Trans. on Audio, Speech and Language Processing, vol. 14, no. 2, pp. 377-392, 2006.
4. D. Povey and P.C. Woodland, "Minimum phone error and i-smoothing for improved discriminative training," Proc. of ICASSP, pp. 105-108, 2002.
5. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," Proc. of ICASSP, pp. 961-964, 2005.
6. Y. Li, H. Erdogan, Y. Gao, and E. Marcheret, "Incremental online feature space mllr adaptation for telephony speech recognition," Proc. of ICSLP, pp. 1417-1420, 2002.
7. C. J. Legetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models," Computer Speech and Language, vol. 9, no. 2, pp. 171-186, 1995.
8. G. Saon, D. Povey, and G. Zweig, "Anatomy of an extremely fast lvcsr decoder," Proc. of Interspeech, pp. 549-552, 2005.