International Journal of Electrical and Computer Engineering (IJECE) Vol. 9, No. 5, October 2019, pp. 3642~3648 ISSN: 2088-8708, DOI: 10.11591/ijece.v9i5.pp3642-3648  3642 Journal homepage: http://iaescore.com/journals/index.php/IJECE Speech to text conversion and summarization for effective understanding and documentation Vinnarasu A., Deepa V. Jose Department of Computer Science, CHRIST (Deemed to be University), India Article Info ABSTRACT Article history: Received Jan 17, 2019 Revised Apr 1, 2019 Accepted Apr 10, 2019 Speech, is the most powerful way of communication with which human beings express their thoughts and feelings through different languages. The features of speech differs with each language. However, even while communicating in the same language, the pace and the dialect varies with each person. This creates difficulty in understanding the conveyed message for some people. Sometimes lengthy speeches are also quite difficult to follow due to reasons such as different pronunciation, pace and so on. Speech recognition which is an inter disciplinary field of computational linguistics aids in developing technologies that empowers the recognition and translation of speech into text. Text summarization extracts the utmost important information from a source which is a text and provides the adequate summary of the same. The research work presented in this paper describes an easy and effective method for speech recognition. The speech is converted to the corresponding text and produces summarized text. This has various applications like lecture notes creation, summarizing catalogues for lengthy documents and so on. Extensive experimentation is performed to validate the efficiency of the proposed method. Keywords: Feature extraction Natural language processing Natural language toolkit Speech recognition Text summarization Copyright © 2019 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Vinnarasu A., Department of Computer Science, CHRIST (Deemed to be University), Bengaluru, Karnataka, India. Email: vinnarasu.a@cs.christuniversity.in 1. INTRODUCTION Speech is the most important part of communication between human beings. Though there are different means to express our thoughts and feeling, speech is considered as the main meduim for communication. Speech recognition is the process of making a machine recognize the speech of diffrent people based on certain words or phrases. Variations in the pronunciation are quite evident in each individual’s speech. The original form of the speech is a signal, and a signal is processed such that all the information present in the signal is converted in to the text format. The feature extraction is the process of taking a signal and converting it to the required format with certain logic. Even though speech is the easiest way of communication, there exist some problems with speech recognition like the fluency, pronunciation, broken words, stuttering issues etc. All these have to be addressed while processing a speech. Text summarization is one of the major concepts used in the field of documentation. Lengthy documents are difficult to read and understand as it consumes lot of time. Text summarisation solves this problem by providing a shortened summary of it with semantics. In the proposed work a combination of speech to text conversion and text summarisation is implemented. This hybrid method will aid applications that require brief summary of lengthy speeches which is quite useful for documentation. The flow diagram of the proposed approach is mentioned in Figure 1, in which the speech recognition and text summarization is given as two different modules. The combination