Edinburgh Research Explorer

A Hybrid MaxEnt/HMM Based ASR System

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationProceedings of the 9th European Conference on Speech Communication and Technology
Subtitle of host publicationInterspeech'2005 - Eurospeech
PublisherISCA
Pages3017-3020
Publication statusPublished - 2005
Event9th European Conference on Speech Communication and Technology (Interspeech 2005 - Eurospeech) - Lisbon, Portugal
Duration: 4 Sep 20058 Sep 2005

Conference

Conference9th European Conference on Speech Communication and Technology (Interspeech 2005 - Eurospeech)
CountryPortugal
CityLisbon
Period4/09/058/09/05

Abstract

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.

ID: 27399392