Performance analysis of isolated speech recognition system using Kannada speech database

Research output: Contribution to journalArticle

Abstract

In this article, performance analysis of speech recognition system for different acoustical models has been presented. In the present work, one of the well-known south Indian language named “Kannada” language is considered. Significantly large amount of work has been reported for Automatic Speech Recognition (ASR) in European languages whereas quite a small number of publications can be found in Indian languages. One of the reasons for this gap is that standard speech database in Indian languages is not available. In this study, Kannada speech corpus based on Kannada broadcast news data has been developed. The isolated speaker independent speech recognition system has been developed using Hidden Markov Tool Kit (HTK). The system front-end uses Mel frequency cepstral coefficients (MFCC) and its derivatives as acoustic features whereas acoustical models are developed by using Hidden Markov Models (HMM). Syllable and mono-phone based Kannada dictionaries have been developed in this study. Various mono-phone models considered in this work are word-level, syllable-level and phone-level models. Further, performance evaluation of mono-phone and tri-phone acoustical models for large sized dictionary also carried out. The best word recognition accuracies of 67.82% and 70.56% are reported for mono-phone and tri-phone based systems respectively. The recognition results for different HMM based acoustical models are obtained and hence the recognition performance has been analyzed.

Original languageEnglish
Pages (from-to)1849-1866
Number of pages18
JournalPertanika Journal of Science and Technology
Volume26
Issue number4
Publication statusPublished - 01-10-2018

Fingerprint

Speech recognition
Language
Databases
Hidden Markov models
Glossaries
Acoustics
Publications
analysis
speech
Derivatives
acoustics

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Chemical Engineering(all)
  • Environmental Science(all)
  • Agricultural and Biological Sciences(all)

Cite this

@article{fe3a845b3bbe4eb4ae7f15bac76173b3,
title = "Performance analysis of isolated speech recognition system using Kannada speech database",
abstract = "In this article, performance analysis of speech recognition system for different acoustical models has been presented. In the present work, one of the well-known south Indian language named “Kannada” language is considered. Significantly large amount of work has been reported for Automatic Speech Recognition (ASR) in European languages whereas quite a small number of publications can be found in Indian languages. One of the reasons for this gap is that standard speech database in Indian languages is not available. In this study, Kannada speech corpus based on Kannada broadcast news data has been developed. The isolated speaker independent speech recognition system has been developed using Hidden Markov Tool Kit (HTK). The system front-end uses Mel frequency cepstral coefficients (MFCC) and its derivatives as acoustic features whereas acoustical models are developed by using Hidden Markov Models (HMM). Syllable and mono-phone based Kannada dictionaries have been developed in this study. Various mono-phone models considered in this work are word-level, syllable-level and phone-level models. Further, performance evaluation of mono-phone and tri-phone acoustical models for large sized dictionary also carried out. The best word recognition accuracies of 67.82{\%} and 70.56{\%} are reported for mono-phone and tri-phone based systems respectively. The recognition results for different HMM based acoustical models are obtained and hence the recognition performance has been analyzed.",
author = "Ananthakrishna Thalengala and Kumara Shama and Maithri Mangalore",
year = "2018",
month = "10",
day = "1",
language = "English",
volume = "26",
pages = "1849--1866",
journal = "Pertanika Journal of Science and Technology",
issn = "0128-7680",
publisher = "Universiti Putra Malaysia",
number = "4",

}

Performance analysis of isolated speech recognition system using Kannada speech database. / Thalengala, Ananthakrishna; Shama, Kumara; Mangalore, Maithri.

In: Pertanika Journal of Science and Technology, Vol. 26, No. 4, 01.10.2018, p. 1849-1866.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Performance analysis of isolated speech recognition system using Kannada speech database

AU - Thalengala, Ananthakrishna

AU - Shama, Kumara

AU - Mangalore, Maithri

PY - 2018/10/1

Y1 - 2018/10/1

N2 - In this article, performance analysis of speech recognition system for different acoustical models has been presented. In the present work, one of the well-known south Indian language named “Kannada” language is considered. Significantly large amount of work has been reported for Automatic Speech Recognition (ASR) in European languages whereas quite a small number of publications can be found in Indian languages. One of the reasons for this gap is that standard speech database in Indian languages is not available. In this study, Kannada speech corpus based on Kannada broadcast news data has been developed. The isolated speaker independent speech recognition system has been developed using Hidden Markov Tool Kit (HTK). The system front-end uses Mel frequency cepstral coefficients (MFCC) and its derivatives as acoustic features whereas acoustical models are developed by using Hidden Markov Models (HMM). Syllable and mono-phone based Kannada dictionaries have been developed in this study. Various mono-phone models considered in this work are word-level, syllable-level and phone-level models. Further, performance evaluation of mono-phone and tri-phone acoustical models for large sized dictionary also carried out. The best word recognition accuracies of 67.82% and 70.56% are reported for mono-phone and tri-phone based systems respectively. The recognition results for different HMM based acoustical models are obtained and hence the recognition performance has been analyzed.

AB - In this article, performance analysis of speech recognition system for different acoustical models has been presented. In the present work, one of the well-known south Indian language named “Kannada” language is considered. Significantly large amount of work has been reported for Automatic Speech Recognition (ASR) in European languages whereas quite a small number of publications can be found in Indian languages. One of the reasons for this gap is that standard speech database in Indian languages is not available. In this study, Kannada speech corpus based on Kannada broadcast news data has been developed. The isolated speaker independent speech recognition system has been developed using Hidden Markov Tool Kit (HTK). The system front-end uses Mel frequency cepstral coefficients (MFCC) and its derivatives as acoustic features whereas acoustical models are developed by using Hidden Markov Models (HMM). Syllable and mono-phone based Kannada dictionaries have been developed in this study. Various mono-phone models considered in this work are word-level, syllable-level and phone-level models. Further, performance evaluation of mono-phone and tri-phone acoustical models for large sized dictionary also carried out. The best word recognition accuracies of 67.82% and 70.56% are reported for mono-phone and tri-phone based systems respectively. The recognition results for different HMM based acoustical models are obtained and hence the recognition performance has been analyzed.

UR - http://www.scopus.com/inward/record.url?scp=85055851710&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055851710&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85055851710

VL - 26

SP - 1849

EP - 1866

JO - Pertanika Journal of Science and Technology

JF - Pertanika Journal of Science and Technology

SN - 0128-7680

IS - 4

ER -