Phoneme Modeling for Speech Recognition in Kannada using Hidden Markov Model

Kannadaguli, Prashanth and Ananthakrishna, T (2015) Phoneme Modeling for Speech Recognition in Kannada using Hidden Markov Model. In: International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES)-2015, 20/02/2015, National Institute of Technology, Calicut, India..

[img] PDF
DisplayPdf3.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy


We build an automatic phoneme recognition system based on Hidden Markov Modeling (HMM) which is a Dynamic modeling scheme. Models were built by using Stochastic pattern recognition and Acoustic phonetic schemes to recognise phonemes. Since our native language is Kannada, a rich South Indian Language, we have used 15 Kannada phonemes to train and test these models. Since Mel – Frequency Cepstral Coefficients (MFCC) are well known Acoustic features of speech[1,2], we have used the same in speech feature extraction. Finally performance analysis of models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields good results and can be used in developing Automatic Speech Recognition systems.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Phoneme Modeling; HMM; Pattern Recognition; MFCC; PER; Kannada
Subjects: Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 07 Jan 2016 14:48
Last Modified: 07 Jan 2016 14:48

Actions (login required)

View Item View Item