Phoneme modeling for speech recognition in Kannada using Hidden Markov Model

Prashanth Kannadaguli, Ananthakrishna Thalengala

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2015
EditorsSuresh Rangan, Vinod Pathari
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479918232
DOIs
Publication statusPublished - 21-04-2015
Event2015 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2015 - Calicut, India
Duration: 19-02-201521-02-2015

Publication series

Name2015 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2015

Conference

Conference2015 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2015
Country/TerritoryIndia
CityCalicut
Period19-02-1521-02-15

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Software

Fingerprint

Dive into the research topics of 'Phoneme modeling for speech recognition in Kannada using Hidden Markov Model'. Together they form a unique fingerprint.

Cite this