Belief Hidden Markov Model for speech recognition
This work addresses cost reduction for speech recognition systems, but it appears incremental as it modifies an existing HMM framework.
The paper tackles the high cost of speech recognition systems by proposing a belief HMM approach instead of probabilistic HMMs, resulting in a model that can be trained with only one example per acoustic unit and achieves good recognition rates.
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.