Review of Features and Classification for Spoken Indian Language Recognition using Deep Learning and Machine Learning Techniques

Abstract

The most common and organic method of interpersonal communication is speech. Humanity has long aspired to creating a computer with human-like comprehension and communication abilities. To recognize language (words and phrases) using voice signals, multilingual countries like India must be taken into account. More research on speech has been demanded by specialists over the past ten years. Researchers require a specific database, or previously recorded collection of information, for that specific recognition system when they seek to construct it. There are several speech databases available for European languages, but only a small number for Indian languages. The several Speech Databases developed in various Indian languages for Text to Speech, Speaker Identification and Speech Identification systems are discussed in this article. To accurately identify the spoken language, first need to collect information from speech signal. In the initial step of the pre-processing phase, audio feature based approach were used, and then deep learning and machine learning classification methods. This survey will explore a variety of feature extraction methods as well as classification methods.