Noise robustness in speech to speech translation

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 2797-2800

  Liu, Fu Hua ^a   Gao, Yuqing ^a   Gu, Liang ^a   Picheny, Michael ^a  

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

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; SIGNAL TO NOISE RATIO; SPEECH; SPEECH COMMUNICATION;

ACOUSTIC MODEL; NOISE ROBUSTNESS; PRE-PROCESSING; QUANTITATIVE MEASURES; RECOGNITION ACCURACY; SPEECH-TO-SPEECH TRANSLATION; TRAINING TECHNIQUES; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 85009168223     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. F.-H. Liu, et al, "Use of Statistical N-Gram Models in Natural Language Generation for Machine Translation", ICASSP-2003, 2003.
2. K. Papineni, et al, "Bleu: A Method for Automatic Evaluation of Machine Translation", Research Report RC22176, IBM, Sept. 2001.
3. A. Berger, et al, "A Maximum Entropy Approach to Natural Language Processing", Computer Linguistics, Vol. 22, No. 1, pp. 39-71, 1996.
4. A. Lavie, et al, "Janus-III: Speech-to-Speech Translation in Multiple Languages", Proceedings of ICASSP-97, 1997
5. W. Wahlster, ed., Verbmobile: Foundation of Speech-to-Speech Translation, Springer, 2000.
6. B. Zhou, et al, "Statistical Natural Language Generation for Speechto-Speech Machine Translation Systems", ICSLP-2002, 2002.
7. A. Acero, Acoustical and Environmental Robustness in Automatic Speech Recognition, Kluwer Academic Publishers, Boston, MA, 1993.
8. R. Donovan, et al, "Phrase Splicing and Variable Substitution Using the IBM Trainable Speech Synthesis System", ICASSP-1999, pp. 373-376, 1999.
9. F.-H. Liu, et al, "Efficient Joint Compensation of Speech for the Effects of Additive Noise and Linear Filtering", ICASSP-92, pp. 865-868, 1992.
10. H. Ney, et al, "Algorithms for Statistical Translation of Spoken Language", IEEE Trans. on Speech and Audio Processing, vol.8, no.1, January 2002
11. T. Takezawa, et al, "A Japanese-to-English Speech Translation System: ART-MATRIX", ICSLP-1998, pp. 2779-2782, 1998.
12. K. Davies, et al, "The IBM Conversational Telephony System for Financial Applications", EuroSpeech-1999, pp.275-278, 1999.
13. R. Lippmann, et al, "Multi-Style Training for Robust Isolated-Word Recognition", ICASSP-87, pp. 705-708, 1987