KL-HMM and Probabilistic Lexical Modeling
| Type of publication: | Idiap-RR |
| Citation: | Rasipuram_Idiap-RR-04-2013 |
| Number: | Idiap-RR-04-2013 |
| Year: | 2013 |
| Month: | 2 |
| Institution: | Idiap |
| Abstract: | Kullback-Leibler divergence based hidden Markov model (KL-HMM) is an approach where a posteriori probabilities of phonemes estimated by artificial neural networks (ANN) are modeled directly as feature observation. In this paper, we show the relation between standard HMM-based automatic speech recognition (ASR) approach and KL-HMM approach. More specifically, we show that KL-HMM is a probabilistic lexical modeling approach which is applicable to both HMM/GMM ASR system and hybrid HMM/ANN ASR system. Through experimental studies on DARPA Resource Management task, we show that KL-HMM approach can improve over state-of-the-art ASR system. |
| Keywords: | |
| Projects |
Idiap |
| Authors | |
| Added by: | [ADM] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
