Spoken arabic dialect identification using phonotactic modeling

Fadi Biadsy; Julia Hirschberg; Nizar Habash

Spoken arabic dialect identification using phonotactic modeling

Fadi Biadsy
, Julia Hirschberg
, Nizar Habash

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

125 Scopus citations

Abstract

The Arabic language is a collection of multiple variants, among which Modern Standard Arabic (MSA) has a special status as the formal written standard language of the media, culture and education across the Arab world. The other variants are informal spoken dialects that are the media of communication for daily life. Arabic dialects differ substantially from MSA and each other in terms of phonology, morphology, lexical choice and syntax. In this paper, we describe a system that automatically identifies the Arabic dialect (Gulf, Iraqi, Levantine, Egyptian and MSA) of a speaker given a sample of his/her speech. The phonotactic approach we use proves to be effective in identifying these dialects with considerable overall accuracy - 81.60% using 30s test utterances.

Original language	English
Pages	53-61
Number of pages	9
State	Published - 1 Jan 2009
Externally published	Yes
Event	EACL 2009 Workshop on Computational Approaches to Semitic Languages, SEMITIC@EACL 2009 - Athens, Greece Duration: 31 Mar 2009 → …

Conference

Conference	EACL 2009 Workshop on Computational Approaches to Semitic Languages, SEMITIC@EACL 2009
Country/Territory	Greece
City	Athens
Period	31/03/09 → …

ASJC Scopus subject areas

Computational Theory and Mathematics
Software
Linguistics and Language

Cite this

@conference{e79425888db644859acafcad3cac3368,

title = "Spoken arabic dialect identification using phonotactic modeling",

abstract = "The Arabic language is a collection of multiple variants, among which Modern Standard Arabic (MSA) has a special status as the formal written standard language of the media, culture and education across the Arab world. The other variants are informal spoken dialects that are the media of communication for daily life. Arabic dialects differ substantially from MSA and each other in terms of phonology, morphology, lexical choice and syntax. In this paper, we describe a system that automatically identifies the Arabic dialect (Gulf, Iraqi, Levantine, Egyptian and MSA) of a speaker given a sample of his/her speech. The phonotactic approach we use proves to be effective in identifying these dialects with considerable overall accuracy - 81.60\% using 30s test utterances.",

author = "Fadi Biadsy and Julia Hirschberg and Nizar Habash",

note = "Publisher Copyright: {\textcopyright} 2009 Association for Computational Linguistics.; EACL 2009 Workshop on Computational Approaches to Semitic Languages, SEMITIC@EACL 2009 ; Conference date: 31-03-2009",

year = "2009",

month = jan,

day = "1",

language = "English",

pages = "53--61",

}

TY - CONF

T1 - Spoken arabic dialect identification using phonotactic modeling

AU - Biadsy, Fadi

AU - Hirschberg, Julia

AU - Habash, Nizar

PY - 2009/1/1

Y1 - 2009/1/1

N2 - The Arabic language is a collection of multiple variants, among which Modern Standard Arabic (MSA) has a special status as the formal written standard language of the media, culture and education across the Arab world. The other variants are informal spoken dialects that are the media of communication for daily life. Arabic dialects differ substantially from MSA and each other in terms of phonology, morphology, lexical choice and syntax. In this paper, we describe a system that automatically identifies the Arabic dialect (Gulf, Iraqi, Levantine, Egyptian and MSA) of a speaker given a sample of his/her speech. The phonotactic approach we use proves to be effective in identifying these dialects with considerable overall accuracy - 81.60% using 30s test utterances.

AB - The Arabic language is a collection of multiple variants, among which Modern Standard Arabic (MSA) has a special status as the formal written standard language of the media, culture and education across the Arab world. The other variants are informal spoken dialects that are the media of communication for daily life. Arabic dialects differ substantially from MSA and each other in terms of phonology, morphology, lexical choice and syntax. In this paper, we describe a system that automatically identifies the Arabic dialect (Gulf, Iraqi, Levantine, Egyptian and MSA) of a speaker given a sample of his/her speech. The phonotactic approach we use proves to be effective in identifying these dialects with considerable overall accuracy - 81.60% using 30s test utterances.

UR - https://www.scopus.com/pages/publications/85026860559

M3 - Paper

AN - SCOPUS:85026860559

SP - 53

EP - 61

T2 - EACL 2009 Workshop on Computational Approaches to Semitic Languages, SEMITIC@EACL 2009

Y2 - 31 March 2009

ER -

Spoken arabic dialect identification using phonotactic modeling

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this