A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation

Recognition of code-switching speech is a challenging problem because of three issues. Code-switching is not a simple mixing of two languages, but each has its own phonological, lexical, and grammatical variations. Second, code-switching resources, such as speech and text corpora, are limited and...

Full description

Bibliographic Details
Main Author: Ahmed, Basem H. A.
Format: Thesis
Language:English
Published: 2014
Subjects:
Online Access:http://eprints.usm.my/62374/
http://eprints.usm.my/62374/1/24%20Pages%20from%2000001780802.pdf
_version_ 1848884966322077696
author Ahmed, Basem H. A.
author_facet Ahmed, Basem H. A.
author_sort Ahmed, Basem H. A.
building USM Institutional Repository
collection Online Access
description Recognition of code-switching speech is a challenging problem because of three issues. Code-switching is not a simple mixing of two languages, but each has its own phonological, lexical, and grammatical variations. Second, code-switching resources, such as speech and text corpora, are limited and difficult to collect. Therefore, creating codeswitching speech recognition models may require a different strategy from that typically used for monolingual automatic speech recognition (ASR). Third, a segment of language switching in an utterance can be as short as a word or as long as an utterance itself. This variation may make language identification difficult. In this thesis, we propose a novel approach to achieve automatic recognition of code-switching speech. The proposed method consists of two phases, namely, ASR and rescoring. The framework uses parallel automatic speech recognizers for speech recognition. We also put forward the usage of an acoustic model adaptation approach known as hybrid approach of interpolation and merging to cross-adapt acoustic models of different languages to recognize code-switching speech better. In pronunciation modeling, we propose an approach to model the pronunciation of non-native accented speech for an ASR system. Our approach is tested on two code-switching corpora: Malay-English and Mandarin-English.
first_indexed 2025-11-15T19:15:06Z
format Thesis
id usm-62374
institution Universiti Sains Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T19:15:06Z
publishDate 2014
recordtype eprints
repository_type Digital Repository
spelling usm-623742025-05-29T01:44:31Z http://eprints.usm.my/62374/ A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation Ahmed, Basem H. A. QA75.5-76.95 Electronic computers. Computer science Recognition of code-switching speech is a challenging problem because of three issues. Code-switching is not a simple mixing of two languages, but each has its own phonological, lexical, and grammatical variations. Second, code-switching resources, such as speech and text corpora, are limited and difficult to collect. Therefore, creating codeswitching speech recognition models may require a different strategy from that typically used for monolingual automatic speech recognition (ASR). Third, a segment of language switching in an utterance can be as short as a word or as long as an utterance itself. This variation may make language identification difficult. In this thesis, we propose a novel approach to achieve automatic recognition of code-switching speech. The proposed method consists of two phases, namely, ASR and rescoring. The framework uses parallel automatic speech recognizers for speech recognition. We also put forward the usage of an acoustic model adaptation approach known as hybrid approach of interpolation and merging to cross-adapt acoustic models of different languages to recognize code-switching speech better. In pronunciation modeling, we propose an approach to model the pronunciation of non-native accented speech for an ASR system. Our approach is tested on two code-switching corpora: Malay-English and Mandarin-English. 2014-05 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/62374/1/24%20Pages%20from%2000001780802.pdf Ahmed, Basem H. A. (2014) A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation. PhD thesis, Perpustakaan Hamzah Sendut.
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Ahmed, Basem H. A.
A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
title A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
title_full A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
title_fullStr A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
title_full_unstemmed A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
title_short A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
title_sort framework for automatic code switching speech recognition with multilingual acoustic and pronunciation models adaptation
topic QA75.5-76.95 Electronic computers. Computer science
url http://eprints.usm.my/62374/
http://eprints.usm.my/62374/1/24%20Pages%20from%2000001780802.pdf