Third European Conference on Speech Communication and Technology

Berlin, Germany
September 22-25, 1993


Performance Comparison of Hidden Markov Models and Neural Networks for Task Dependent and Independent Isolated Word Recognition

Hervé Bourlard, Jean-Marc Boite, Bart D'Hoore, Marco Saerens

Lernout & Hauspie Speech Products, Ieper, Belgium

In this paper, we compare the recognition performance which can be achieved for speaker independent isolated word recognition over the telephone line by standard phonemic Hidden Markov Models (HMMs) with a hybrid approach using HMMs together with a Multilayer Perceptron (MLP) to estimate the HMM emission probabilities. Recently, the latter approach has been shown particularly efficient for a large vocabulary, speaker independent, continuous speech recognition task (i.e. DARPA Resource Management database). Since this approach seems to be more robust for simple context-independent phoneme models, the aim of this paper is to compare the performance which can be achieved in the case of task independent training, i.e. when the phonemic models are trained on a database which does not contain the words used in the targeted application.

Full Paper

Bibliographic reference.  Bourlard, Hervé / Boite, Jean-Marc / D'Hoore, Bart / Saerens, Marco (1993): "Performance comparison of hidden Markov models and neural networks for task dependent and independent isolated word recognition", In EUROSPEECH'93, 1925-1928.