Beyerlein P. Discriminative model combination. In: Proceedings of the 1997 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). Santa Barbara, USA: IEEE, 1997. 238-245
[2]
Hoffmeister B, Liang R Y, Schlüter R, Ney H. Log-linear model combination with word-dependent scaling factors. In: Proceedings of the 10th Annual Conference of the International Speech Communication Association (Interspeech). Brighton, UK: Interspeech, 2009. 248-541
[3]
Liu X Y, Gales M J F, Hieronymus J L, Woodland P C. Language model combination and adaptation using weighted finite state transducers. In: Proceedings of the 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dallas, USA: IEEE, 2010. 5390-5393
[4]
Povey D, Woodland P C. Minimum phone error and I-smoothing for improved discriminative training. In: Proceedings of the 2002 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Orlando, USA: IEEE, 2002. 105-108
[5]
Wu Ya-Hui, Liu Gang, Guo Jun. Research on model combination based on model confusion. Acta Automatica Sinica, 2009, 35(5): 551-555 (吴娅辉, 刘刚, 郭军. 基于模型混淆度的模型组合算法研究. 自动化学报, 2009, 35(5): 551-555)
[6]
Gao S, Lee C H. A discriminative decision tree learning approach to acoustic modeling. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech). Geneva, Switzerland: ISCA, 2003. 1833- 1836
[7]
Chang E, Shi Y, Zhou J L, Huang C. Speech lab in a box: a Mandarin speech toolbox to jumpstart speech related research. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech). Aalborg, Denmark: ISCA, 2001. 2779-2782
Huang H, Zhu J. Discriminative incorporation of explicitly trained tone models into lattice based rescoring for Mandarin speech recognition. In: Proceedings of the 2008 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Las Vagas, USA: IEEE, 2008. 1541- 1544
[10]
Liu X Y, Gales M J F, Woodland P C. Use of contexts in language model interpolation and adaptation. In: Proceedings of the 10th Annual Conference of the International Speech Communication Association (Interspeech). Brighton, UK: Interspeech, 2009. 360-363
[11]
Ellis D P W, Singh R, Sivadas S. Tandem acoustic modeling in large-vocabulary recognition. In: Proceedings of the 2001 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Salt Lake City, USA: IEEE, 2001. 1201-1204
[12]
Povey D. Discriminative Training for Large Vocabulary Speech Recognition [Ph.D. dissertation], Cambridge University, UK, 2004
[13]
Young S J, Odell J J, Woodland P C. Tree-based state tying for high accuracy acoustic modelling. In: Proceedings of the 1994 Workshop on Human Language Technology. Stroudsburg, USA: ACL, 1994. 307-312
[14]
Wiesler S, Heigold G, Nuβ baum-Thom M, Schlüter R, Ney H. A discriminative splitting criterion for phonetic decision trees. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech). Makuhari, Japan: ISCA, 2010. 54-57
[15]
Qian Y, Lee T, Li Y J. Overlapped ditone modeling for tone recognition in continuous Cantonese speech. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech). Geneva, Switzerland: ISCA, 2003. 1845-1848
[16]
The ICSI Quicknet Tools [Online], available: http://www. icsi.berkeley.edu/Speech/qn.html, March 15, 2012
