Training products of experts by minimizing contrastive divergence
Neural Computation
Investigation of silicon auditory models and generalization of linear discriminant analysis for improved speech recognition
Discriminative training and maximum entropy models for statistical machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
Continuous space language models
Computer Speech and Language
Improvements in recognition of conversational telephone speech
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Modeling characters versuswords for mandarin speech recognition
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Product of Gaussians for speech recognition
Computer Speech and Language
Domain adaptation of maximum entropy language models
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Use of contexts in language model interpolation and adaptation
Computer Speech and Language
| Hi-index | 0.00 |
State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple sub-systems that may even be developed at different sites. Cross system adaptation, in which model adaptation is performed using the outputs from another sub-system, can be used as an alternative to hypothesis level combination schemes such as ROVER. Normally cross adaptation is only performed on the acoustic models. However, there are many other levels in LVCSR systems' modelling hierarchy where complimentary features may be exploited, for example, the sub-word and the word level, to further improve cross adaptation based system combination. It is thus interesting to also cross adapt language models (LMs) to capture these additional useful features. In this paper cross adaptation is applied to three forms of language models, a multi-level LM that models both syllable and word sequences, a word level neural network LM, and the linear combination of the two. Significant error rate reductions of 4.0-7.1% relative were obtained over ROVER and acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations.