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

Prashanth Kannadaguli; Vidya Bhat

doi:10.1109/RETCOMP.2015.7090795

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 proceeding › Conference contribution

10 Citations (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 language	English
Title of host publication	Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781479918355
DOIs	https://doi.org/10.1109/RETCOMP.2015.7090795
Publication status	Published - 01-01-2015
Externally published	Yes
Event	2015 Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2014 - Bangalore, India Duration: 08-01-2015 → 10-01-2015

Conference

Conference	2015 Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2014
Country/Territory	India
City	Bangalore
Period	08-01-15 → 10-01-15

All Science Journal Classification (ASJC) codes

Computer Science(all)

Access to Document

10.1109/RETCOMP.2015.7090795

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

@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 = jan,

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",

note = "2015 Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2014 ; Conference date: 08-01-2015 Through 10-01-2015",

}

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 proceeding › Conference 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

AN - SCOPUS:84929847258

SP - 1

EP - 5

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 Recent and Emerging Trends in Computer and Computational Sciences, RETCOMP 2014

Y2 - 8 January 2015 through 10 January 2015

ER -

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

Abstract

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this