State of Research of Speech Recognition

Abstract

In this chapter, a brief overview derived out of detailed survey of speech recognition works reported from different groups all over the globe in the last two decades is described. Robustness of speech recognition systems toward language variation is the recent trend of research in speech recognition technology. To develop a system which can communicate with human being in any language like any other human being is the foremost requirement of any speech recognition technology for one and all. From the beginning of commercial availability of the speech recognition system, the technology has been dominated by the Hidden Markov Model (HMM) methodology due to its capability of modeling temporal structures of speech and encoding them as a sequence of spectral vectors. However, from the last 10 to 15 years, after the acceptance of neurocomputing as an alternative to HMM, ANN-based methodologies have started to receive attention for application in speech recognition. This is a trend worldwide as part of which a few works have also reported by researchers. India is a country which has vast linguistic variations among its billion plus population. Therefore, it provides a sound area of research toward language-specific speech recognition technology. This review also covers a study on speech recognition works done specifically in certain Indian languages. Most of the work done in Indian languages also uses HMM technology. However, ANN technology is also adopted by a few Indian researchers.