Belief Hidden Markov Model for speech recognition

TL;DR

This paper introduces a belief Hidden Markov Model approach for speech recognition that reduces data requirements and costs by being effective with minimal training data, offering a promising alternative to traditional probabilistic models.

Contribution

The paper proposes a belief HMM framework for speech recognition that is less data-dependent and cost-effective compared to conventional probabilistic HMMs.

Findings

Insensitivity to lack of data

Effective training with only one example per acoustic unit

Achieves good recognition rates

Abstract

Speech Recognition searches to predict the spoken words automatically. These systems are known to be very expensive because of using several pre-recorded hours of speech. Hence, building a model that minimizes the cost of the recognizer will be very interesting. In this paper, we present a new approach for recognizing speech based on belief HMMs instead of proba-bilistic HMMs. Experiments shows that our belief recognizer is insensitive to the lack of the data and it can be trained using only one exemplary of each acoustic unit and it gives a good recognition rates. Consequently, using the belief HMM recognizer can greatly minimize the cost of these systems.