Please use this identifier to cite or link to this item:
|Title:||Discriminative training of language models for speech recognition||Authors:||Kuo, H.-K.J.
|Issue Date:||2002||Citation:||Kuo, H.-K.J.,Fosler-Lussier, E.,Jiang, H.,Lee, C.-H. (2002). Discriminative training of language models for speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 1 : I/325-I/328. ScholarBank@NUS Repository.||Abstract:||In this paper we describe how discriminative training can be applied to language models for speech recognition. Language models are important to guide the speech recognition search, particularly in compensating for mistakes in acoustic decoding. A frequently used measure of the quality of language models is the perplexity; however, what is more important for accurate decoding is not necessarily having the maximum likelihood hypothesis, but rather the best separation of the correct string from the competing, acoustically confusible hypothesis. Discriminative training can help to improve language models for the purpose of speech recognition by improving the separation of the correct hypothesis from the competing hypothesis. We describe the algorithm and demonstrate modest improvements in word and sentence error rates on the DARPA Communicator task without any increase in language model complexity.||Source Title:||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings||URI:||http://scholarbank.nus.edu.sg/handle/10635/40579||ISSN:||15206149|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on May 12, 2022
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.