Hindi Speech Recognition

Akanksha Saxena

Abstract: This work is to develop a speech recognition system for speaker dependent, real time, isolated words of Hindi Language. Speech is a useful and effective communication medium with machines, especially in the environment where keyboard input is awkward or impossible. The Speech Processing technology (Automatic Speech Recognition and Speech Synthesis) has made great progress for European languages. In India, almost three-fourth of the population lives in rural areas and most of the population is unfamiliar with computers and English. It would be a great boon for Indian society if communication with machines, mainly with computers, in native languages can be made possible. It will enable people to interact with computers in their own language and without the use of keyboard. This report is a study of the technology and modeling techniques, having been used for Speech Processing. The focus of the present work is Hindi Speech Recognition.

Keywords: Natural language processing, Hidden Markov Model, Mel frequency cepstral coefficient, Human computer interaction, Viterbi algorithm

How to Cite?: Akanksha Saxena, "Hindi Speech Recognition", Volume 4 Issue 6, June 2015, International Journal of Science and Research (IJSR), Pages: 1431-1435, https://www.ijsr.net/getabstract.php?paperid=SUB155534, DOI: https://dx.doi.org/10.21275/SUB155534