A Survey of Machine Learning Approaches for Speech Recognition

Abstract

Machine learning approaches have been used for a wide range of applications in the recent years. The strength of these approaches mainly lies in their ability to learn from experience. Speech recognition has been area which has gained a lot of popularity in recent years. Siri, Genie, and Cortana are some commonly used examples. The focus of these applications have been to interpret human speech into a set of basic commands for a portable device. In this paper, we present a survey of the some commonly used machine learning approaches for speech recognition. While there are several variations to the speech recognition system, little is known about the challenges associated with each approach. In this paper we present a comparison of the available approaches and highlight the pros and cons of some of the popularly used approaches.