Ragni, A and Gales, MJF (2011) Structured discriminative models for noise robust continuous speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4788-4791. ISSN 1520-6149Full text not available from this repository.
Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features extracted from the observation sequence, and hypothesised word sequence. In previous work these discriminative models have been combined with features derived from generative models for noise-robust speech recognition for continuous digits. This paper extends this work to medium to large vocabulary tasks. The form of the score-space extracted using the generative models, and parameter tying of the discriminative model, are both discussed. Update formulae for both conditional maximum likelihood and minimum Bayes' risk training are described. Experimental results are presented on small and medium to large vocabulary noise-corrupted speech recognition tasks: AURORA 2 and 4. © 2011 IEEE.
|Uncontrolled Keywords:||Conditional Maximum Likelihood Context modelling Minimum Phone Error Noise robustness Structured model|
|Divisions:||Div F > Machine Intelligence|
|Depositing User:||Cron Job|
|Date Deposited:||07 Mar 2014 11:22|
|Last Modified:||08 Dec 2014 02:30|