MU Digital Repository
Logo

Kannada Word Recognition System using HTK

Ananthakrishna, T and Maithri, M and Kumara, Shama (2015) Kannada Word Recognition System using HTK. In: IEEE International Conference INDICON-2015, 17/12/2015, Jamia Millia Islamia University, New Delhi.

[img] PDF
Display1Pdf.pdf - Published Version
Restricted to Registered users only

Download (602kB) | Request a copy

Abstract

In the present work, speech recognition system for Kannada language has been implemented using the Hidden Markov Tool Kit (HTK). The system performance is comparatively studied and evaluated for syllable and phone level models. The Kannada word dictionary of size about 110 words is used in the study and Mel frequency cepstral coefficients (MFCC) are computed in acoustic front-end processing. The system is designed to recognize isolated utterances of Kannada words, which are recorded from a Kannada short story. Baum-Welch algorithm is used to train the Hidden Markov Model (HMM) and Viterbi algorithm for decoding process. The objective of this study is to compare the performances of phone-level and syllable-level acoustical models for small to medium sized Kannada language vocabulary. The results are part of the on-going research work on large vocabulary continuous speech recognition system for Kannada language. Average word recognition accuracy of 97.1% for syllable-level modeling and 98.6% for phone-level modeling has been reported. Analysis of system performance also carried out based on the confusion matrices.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Hidden Markov Tool Kit (HTK), Mel frequency cepstral coefficients (MFCC), Kannada language, Syllable-level and Phone-level modeling
Subjects: Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 11 Jan 2016 09:33
Last Modified: 11 Jan 2016 09:33
URI: http://eprints.manipal.edu/id/eprint/145025

Actions (login required)

View Item View Item