AUTOMATED SPEECH-TO-TEXT CONVERSION SYSTEMS IN BANGLA LANGUAGE: A SYSTEMATIC LITERATURE REVIEW

Abstract

The 4th Industrial Revolution (4IR) is creating a new way of working and impacting all disciplines, industries, and economies. In future days, there will be needed seamless communication with machines and has to deal with an enormous amount of information. As speech is the most natural way of communication for humans, research in Natural Language Processing (NLP) is increasing with time. To make human-computer interaction effortless Speech-to-Text (STT) conversion is particularly important. A lot of research works have been carried out to allow machines to interact with humans naturally in many languages like English, Spanish, Japanese, etc. Bangla is the primary language of Bangladesh and West Bengal of India and is spoken by over 250 million people worldwide. Speech processing in Bangla language is still an open research field. This literature review studies the recent advancements in automated speech to text conversion in Bangla language. In this paper, we present a comprehensive comparative study on the state-of-the-art Bangla speech to text conversion systems in accordance with dataset size, feature extraction techniques, methodologies used, toolkits, and accuracies. Furthermore, challenges associated with Bangla speech processing research, applications of automatic speech to text conversion in different fields of Bangla language along possible future research indications are elaborated in this paper.