Analysis of L2 English Speech Corpus by Automatic Phoneme Alignment

Hajime Tsubaki; Mariko Kondo

Analysis of L2 English Speech Corpus by Automatic Phoneme Alignment

Hajime Tsubaki, Mariko Kondo

School of International Liberal Studies

Research output: Contribution to conference › Paper › peer-review

3 Citations (Scopus)

Abstract

This study tested the application of adapted HTK for automatic alignment of speech corpus of Asian speakers’ English. The HTK tool with TIMIT has problems in aligning non-native speakers’ English. New sets of phoneme sequences for each word were listed to test if an adapted alignment module could accurately analyze pronunciation of Japanese speakers’ English. The new sets of phoneme sequences produced better alignment of Japanese accented English and showed that the L2 incorporated new alignment module could perform more accurate automatic alignment of L2 English data. The same methods should be able to be applied to other language data.

Original language	English
Pages	141-144
Number of pages	4
Publication status	Published - 2011
Event	2011 ISCA International Workshop on Speech and Language Technology in Education, SLaTE 2011 - Venice, Italy Duration: 2011 Aug 24 → 2011 Aug 26

Conference

Conference	2011 ISCA International Workshop on Speech and Language Technology in Education, SLaTE 2011
Country/Territory	Italy
City	Venice
Period	11/8/24 → 11/8/26

Keywords

automatic alignment
HTK
L2 English
speech corpus
TIMIT

ASJC Scopus subject areas

Education
Computer Science (miscellaneous)
Computational Mathematics

Cite this

@conference{c3a6ff34589f477fa98f988909859a5f,

title = "Analysis of L2 English Speech Corpus by Automatic Phoneme Alignment",

abstract = "This study tested the application of adapted HTK for automatic alignment of speech corpus of Asian speakers{\textquoteright} English. The HTK tool with TIMIT has problems in aligning non-native speakers{\textquoteright} English. New sets of phoneme sequences for each word were listed to test if an adapted alignment module could accurately analyze pronunciation of Japanese speakers{\textquoteright} English. The new sets of phoneme sequences produced better alignment of Japanese accented English and showed that the L2 incorporated new alignment module could perform more accurate automatic alignment of L2 English data. The same methods should be able to be applied to other language data.",

keywords = "automatic alignment, HTK, L2 English, speech corpus, TIMIT",

author = "Hajime Tsubaki and Mariko Kondo",

note = "Funding Information: Part of this research was supported by JSPS Grants-in-Aid for Scientific Research, (C) No.22520585, and Sophia University Open Research Center. We would like to express our gratitude to Prof. Yoshinori Sagisaka of GITI, Waseda University for his support with this research. Publisher Copyright: {\textcopyright} SLaTE 2011. All Rights Reserved.; 2011 ISCA International Workshop on Speech and Language Technology in Education, SLaTE 2011 ; Conference date: 24-08-2011 Through 26-08-2011",

year = "2011",

language = "English",

pages = "141--144",

}

TY - CONF

T1 - Analysis of L2 English Speech Corpus by Automatic Phoneme Alignment

AU - Tsubaki, Hajime

AU - Kondo, Mariko

N1 - Funding Information: Part of this research was supported by JSPS Grants-in-Aid for Scientific Research, (C) No.22520585, and Sophia University Open Research Center. We would like to express our gratitude to Prof. Yoshinori Sagisaka of GITI, Waseda University for his support with this research. Publisher Copyright: © SLaTE 2011. All Rights Reserved.

PY - 2011

Y1 - 2011

N2 - This study tested the application of adapted HTK for automatic alignment of speech corpus of Asian speakers’ English. The HTK tool with TIMIT has problems in aligning non-native speakers’ English. New sets of phoneme sequences for each word were listed to test if an adapted alignment module could accurately analyze pronunciation of Japanese speakers’ English. The new sets of phoneme sequences produced better alignment of Japanese accented English and showed that the L2 incorporated new alignment module could perform more accurate automatic alignment of L2 English data. The same methods should be able to be applied to other language data.

AB - This study tested the application of adapted HTK for automatic alignment of speech corpus of Asian speakers’ English. The HTK tool with TIMIT has problems in aligning non-native speakers’ English. New sets of phoneme sequences for each word were listed to test if an adapted alignment module could accurately analyze pronunciation of Japanese speakers’ English. The new sets of phoneme sequences produced better alignment of Japanese accented English and showed that the L2 incorporated new alignment module could perform more accurate automatic alignment of L2 English data. The same methods should be able to be applied to other language data.

KW - automatic alignment

KW - HTK

KW - L2 English

KW - speech corpus

KW - TIMIT

UR - http://www.scopus.com/inward/record.url?scp=84874239344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874239344&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84874239344

SP - 141

EP - 144

T2 - 2011 ISCA International Workshop on Speech and Language Technology in Education, SLaTE 2011

Y2 - 24 August 2011 through 26 August 2011

ER -

Analysis of L2 English Speech Corpus by Automatic Phoneme Alignment

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this