Improving LVCSR system combination using neural network language model cross adaptation

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2011, Pages 2857-2860

  Liu, X ^a   Gales, M J F ^a   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODEL; ADAPTATION FRAMEWORK; ADAPTATION TECHNIQUES; CROSS SYSTEMS; ERROR RATE; LANGUAGE MODEL; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; MULTIPLE SUBSYSTEMS; NETWORK LANGUAGE; SUB-SYSTEMS; SYSTEM COMBINATION;

CONTINUOUS SPEECH RECOGNITION; NEURAL NETWORKS;

COMPUTATIONAL LINGUISTICS;

EID: 84865740155     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Y. Bengio et al. (2001). "A neural probabilistic language model", J. of Machine Learning Research, Vol. 3, No. 2, 2001.
2. L. Chen et al. (2001). Language Model Adaptation For Broadcast News Transcription, in Proc. ISCA ITRW'01.
3. S. M. Chu et al. (2010). The 2009 IBM GALE Mandarin Broadcast Transcription System, in Proc. IEEE ICASSP2010.
4. A. Emami & L. Mangu, "Empirical study of neural network language models of Arabic speech recognition", in Proc. IEEE ASRU2007.
5. G. Evermann & P.C. Woodland (2000). Posterior Probability Decoding, Confidence Estimation and System Combination, in Proc. Speech Transcription Workshop 2000.
6. M. Federico (1999). Efficient Language Model Adaptation Through MDI Estimation, in Proc. EuroSpeech'99.
7. J. G. Fiscus (1997). A Post-Processing System to Yield Reduced Word Error Rates: Recogniser Output Voting Error Reduction (ROVER). In Proc. IEEE ASRU'97.
8. L. Lamel et al. (2011). Improved Models for Mandarin Speechto- text Transcription, to appear in Proc. IEEE ICASSP2011.
9. X. Liu, M. J. F. Gales & P. C. Woodland (2009). Use of Contexts in Language Model Interpolation and Adaptation, in Proc. Interspeech'09.
10. X. Liu, M. J. F. Gales & P. C. Woodland (2010). Language Model Cross Adaptation For LVCSR System Combination, in Proc. Interspeech'10.
11. X. Liu, M. J. F. Gales, J. L. Hieronymus & P. C. Woodland (2010). Language Model Combination and Adaptation Using Weighted Finite State Transducers, in Proc. IEEE ICASSP2010.
12. X. Liu, M. J. F. Gales, J. L. Hieronymus & P. C. Woodland (2011). Investigation of Acoustic Units for LVCSR Systems, to appear in Proc. IEEE ICASSP2011.
13. M. Mohri & M. Riley. Network optimizations for large vocabulary speech recognition. Speech Communication, 25:3, 1998.
14. T. Ng et al. (2010). Jointly Optimized Discriminative Features for Speech Recognition, in Proc. Interspeech'10.
15. J. Park, X. Liu, M. J. F. Gales & P. C. Woodland (2010). Improved Neural Network Based Language Modelling and Adaptation, in Proc. Interspeech'10.
16. B. Peskin et al. (1999). Improvemnets in Recognition of Conversational Telephone Speech, in Proc. IEEE ICASSP1999.
17. R. Schwartz et al. (2004). Speech Recognition in Multiple Languages and Domains: The 2003 BBN/LIMSI EARS System, in Proc. IEEE ICASSP2004.
18. H. Schwenk, "Continuous space language models", Computer Speech and Language, Vol. 21, 2007, pp. 492-518.
19. P. C. Woodland et al. (1995). The 1994 HTK Large Vocabulary Speech Recognition System, in Proc. IEEE ICASSP1995.
20. P. C. Woodland et al. (2004). SuperEARS: Multi-site Broadcast News System, in Proc. Rich Transcription Workshop 2004.