The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Models (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 recognition 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.
|Title of host publication||Proceedings of the 9th European Conference on Speech Communication and Technology|
|Subtitle of host publication||Interspeech'2005 - Eurospeech|
|Publication status||Published - 2005|
|Event||9th European Conference on Speech Communication and Technology (Interspeech 2005 - Eurospeech) - Lisbon, Portugal|
Duration: 4 Sep 2005 → 8 Sep 2005
|Conference||9th European Conference on Speech Communication and Technology (Interspeech 2005 - Eurospeech)|
|Period||4/09/05 → 8/09/05|