A Hybrid MaxEnt/HMM Based ASR System

[edit]

Yasser Hifny
Steve Renals, University of Edinburgh
Neil D. Lawrence, University of Sheffield

in Proceedings of Interspeech 2005 --- 9th European Conference on Speech Communication and Technology

Related Material

Abstract

The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Model (HMM) for continuous speech recognition based on the Maximum Entropy (MaxEnt) principle. The MaxEnt models can estimate the posterior probabilities directly as with Hybrid NN/HMM connectionist speech recogniton systems. In particular, a new acoustic modelling based on discriminative MaxEnt models is formulated and is being developed to replace the generative Gaussian Mixture Models (GMM) commonly used to model acoustic variability. Initial experimental results using the TIMIT phone task are reported.


@InProceedings{hifny-maxent05,
  title = 	 {A Hybrid MaxEnt/HMM Based ASR System},
  author = 	 {Yasser Hifny and Steve Renals and Neil D. Lawrence},
  booktitle = 	 {Proceedings of Interspeech 2005 --- 9th European Conference on Speech Communication and Technology},
  year = 	 {2005},
  month = 	 {00},
  organization = {Lisbon, Portugal},
  edit = 	 {https://github.com/lawrennd//publications/edit/gh-pages/_posts/2005-09-04-hifny-maxent05.md},
  url =  	 {http://inverseprobability.com/publications/hifny-maxent05.html},
  abstract = 	 {The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Model (HMM) for continuous speech recognition based on the Maximum Entropy (MaxEnt) principle. The MaxEnt models can estimate the posterior probabilities directly as with Hybrid NN/HMM connectionist speech recogniton systems. In particular, a new acoustic modelling based on discriminative MaxEnt models is formulated and is being developed to replace the generative Gaussian Mixture Models (GMM) commonly used to model acoustic variability. Initial experimental results using the TIMIT phone task are reported.},
  key = 	 {Hifny:maxent05},
  linkpdf = 	 {ftp://ftp.dcs.shef.ac.uk/home/neil/hifny-eurospeech05.pdf},
  OPTgroup = 	 {}
 

}
%T A Hybrid MaxEnt/HMM Based ASR System
%A Yasser Hifny and Steve Renals and Neil D. Lawrence
%B 
%C Proceedings of Interspeech 2005 --- 9th European Conference on Speech Communication and Technology
%D 
%F hifny-maxent05	
%P --
%R 
%U http://inverseprobability.com/publications/hifny-maxent05.html
%X The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Model (HMM) for continuous speech recognition based on the Maximum Entropy (MaxEnt) principle. The MaxEnt models can estimate the posterior probabilities directly as with Hybrid NN/HMM connectionist speech recogniton systems. In particular, a new acoustic modelling based on discriminative MaxEnt models is formulated and is being developed to replace the generative Gaussian Mixture Models (GMM) commonly used to model acoustic variability. Initial experimental results using the TIMIT phone task are reported.
TY  - CPAPER
TI  - A Hybrid MaxEnt/HMM Based ASR System
AU  - Yasser Hifny
AU  - Steve Renals
AU  - Neil D. Lawrence
BT  - Proceedings of Interspeech 2005 --- 9th European Conference on Speech Communication and Technology
PY  - 2005/09/04
DA  - 2005/09/04	
ID  - hifny-maxent05	
SP  - 
EP  - 
L1  - ftp://ftp.dcs.shef.ac.uk/home/neil/hifny-eurospeech05.pdf
UR  - http://inverseprobability.com/publications/hifny-maxent05.html
AB  - The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Model (HMM) for continuous speech recognition based on the Maximum Entropy (MaxEnt) principle. The MaxEnt models can estimate the posterior probabilities directly as with Hybrid NN/HMM connectionist speech recogniton systems. In particular, a new acoustic modelling based on discriminative MaxEnt models is formulated and is being developed to replace the generative Gaussian Mixture Models (GMM) commonly used to model acoustic variability. Initial experimental results using the TIMIT phone task are reported.
ER  -

Hifny, Y., Renals, S. & Lawrence, N.D.. (2005). A Hybrid MaxEnt/HMM Based ASR System. Proceedings of Interspeech 2005 --- 9th European Conference on Speech Communication and Technology :-