A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada

Prashanth Kannadaguli, Vidya Bhat

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

1 Citation (Scopus)

Abstract

We build and compare phoneme recognition systems based on Bayesian Multivariate Modeling scheme and Hidden Markov Modeling (HMM) scheme. Both 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, we have used the same in speech feature extraction. Finally performance analysis of both models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields better results over Static modeling and can be used in developing Automatic Speech Recognition systems.

Original languageEnglish
Title of host publicationRecent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781479918355
DOIs
Publication statusPublished - 01-01-2015
Externally publishedYes
Event2015 Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2014 - Bangalore, India
Duration: 08-01-201510-01-2015

Conference

Conference2015 Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2014
CountryIndia
CityBangalore
Period08-01-1510-01-15

Fingerprint

Acoustics
Speech analysis
Speech recognition
Pattern recognition
Feature extraction

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Kannadaguli, P., & Bhat, V. (2015). A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada. In Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015 (pp. 1-5). [7090795] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RETCOMP.2015.7090795
Kannadaguli, Prashanth ; Bhat, Vidya. / A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada. Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1-5
@inproceedings{640fb7a7124e4c86b144b409eefde73a,
title = "A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada",
abstract = "We build and compare phoneme recognition systems based on Bayesian Multivariate Modeling scheme and Hidden Markov Modeling (HMM) scheme. Both 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, we have used the same in speech feature extraction. Finally performance analysis of both models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields better results over Static modeling and can be used in developing Automatic Speech Recognition systems.",
author = "Prashanth Kannadaguli and Vidya Bhat",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/RETCOMP.2015.7090795",
language = "English",
pages = "1--5",
booktitle = "Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Kannadaguli, P & Bhat, V 2015, A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada. in Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015., 7090795, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 2015 Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2014, Bangalore, India, 08-01-15. https://doi.org/10.1109/RETCOMP.2015.7090795

A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada. / Kannadaguli, Prashanth; Bhat, Vidya.

Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1-5 7090795.

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

TY - GEN

T1 - A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada

AU - Kannadaguli, Prashanth

AU - Bhat, Vidya

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We build and compare phoneme recognition systems based on Bayesian Multivariate Modeling scheme and Hidden Markov Modeling (HMM) scheme. Both 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, we have used the same in speech feature extraction. Finally performance analysis of both models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields better results over Static modeling and can be used in developing Automatic Speech Recognition systems.

AB - We build and compare phoneme recognition systems based on Bayesian Multivariate Modeling scheme and Hidden Markov Modeling (HMM) scheme. Both 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, we have used the same in speech feature extraction. Finally performance analysis of both models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields better results over Static modeling and can be used in developing Automatic Speech Recognition systems.

UR - http://www.scopus.com/inward/record.url?scp=84929847258&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929847258&partnerID=8YFLogxK

U2 - 10.1109/RETCOMP.2015.7090795

DO - 10.1109/RETCOMP.2015.7090795

M3 - Conference contribution

SP - 1

EP - 5

BT - Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kannadaguli P, Bhat V. A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada. In Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1-5. 7090795 https://doi.org/10.1109/RETCOMP.2015.7090795