Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages

Nur Endah Safitri; Amalia Zahra; Mirna Adriani

doi:10.1016/j.procs.2016.04.047

Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages

Nur Endah Safitri, Amalia Zahra, Mirna Adriani

Department of Computer Science

Research output: Contribution to journal › Conference article › peer-review

19 Citations (Scopus)

Abstract

Research in the field of spoken language identification (spoken LID) on local languages helps to extend the outreach of technology to local language speakers. This research also contributes to the preservation of local languages. In this paper, we report our work on identifying spoken data in three local Indonesian languages: Minangkabau, Sundanese and Javanese. Statistical phonotactics models are created to map the speech signals into the language used by the speaker. We use two phonotactics methods, namely Phone Recognition followed by Language Modelling (PRLM) and Parallel Phone Recognition followed by Language Modelling (PPRLM). PRLM method shows the highest accuracy using the phone recognizer trained for English and Russian with the average of 77.42% and 75.94% respectively.

Original language	English
Pages (from-to)	182-187
Number of pages	6
Journal	Procedia Computer Science
Volume	81
DOIs	https://doi.org/10.1016/j.procs.2016.04.047
Publication status	Published - 2016
Event	5th Workshop on Spoken Language Technologies for Under-resourced languages, SLTU 2016 - Yogyakarta, Indonesia Duration: 9 May 2016 → 12 May 2016

Keywords

phonotactic methods
spoken language identification

Access to Document

10.1016/j.procs.2016.04.047

Cite this

@article{5f87d53c6c614cddac3f21144ec3f667,

title = "Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages",

abstract = "Research in the field of spoken language identification (spoken LID) on local languages helps to extend the outreach of technology to local language speakers. This research also contributes to the preservation of local languages. In this paper, we report our work on identifying spoken data in three local Indonesian languages: Minangkabau, Sundanese and Javanese. Statistical phonotactics models are created to map the speech signals into the language used by the speaker. We use two phonotactics methods, namely Phone Recognition followed by Language Modelling (PRLM) and Parallel Phone Recognition followed by Language Modelling (PPRLM). PRLM method shows the highest accuracy using the phone recognizer trained for English and Russian with the average of 77.42% and 75.94% respectively.",

keywords = "phonotactic methods, spoken language identification",

author = "Safitri, {Nur Endah} and Amalia Zahra and Mirna Adriani",

note = "Publisher Copyright: {\textcopyright} 2016 The Authors.; 5th Workshop on Spoken Language Technologies for Under-resourced languages, SLTU 2016 ; Conference date: 09-05-2016 Through 12-05-2016",

year = "2016",

doi = "10.1016/j.procs.2016.04.047",

language = "English",

volume = "81",

pages = "182--187",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier BV",

}

TY - JOUR

T1 - Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages

AU - Safitri, Nur Endah

AU - Zahra, Amalia

AU - Adriani, Mirna

PY - 2016

Y1 - 2016

N2 - Research in the field of spoken language identification (spoken LID) on local languages helps to extend the outreach of technology to local language speakers. This research also contributes to the preservation of local languages. In this paper, we report our work on identifying spoken data in three local Indonesian languages: Minangkabau, Sundanese and Javanese. Statistical phonotactics models are created to map the speech signals into the language used by the speaker. We use two phonotactics methods, namely Phone Recognition followed by Language Modelling (PRLM) and Parallel Phone Recognition followed by Language Modelling (PPRLM). PRLM method shows the highest accuracy using the phone recognizer trained for English and Russian with the average of 77.42% and 75.94% respectively.

AB - Research in the field of spoken language identification (spoken LID) on local languages helps to extend the outreach of technology to local language speakers. This research also contributes to the preservation of local languages. In this paper, we report our work on identifying spoken data in three local Indonesian languages: Minangkabau, Sundanese and Javanese. Statistical phonotactics models are created to map the speech signals into the language used by the speaker. We use two phonotactics methods, namely Phone Recognition followed by Language Modelling (PRLM) and Parallel Phone Recognition followed by Language Modelling (PPRLM). PRLM method shows the highest accuracy using the phone recognizer trained for English and Russian with the average of 77.42% and 75.94% respectively.

KW - phonotactic methods

KW - spoken language identification

UR - http://www.scopus.com/inward/record.url?scp=84976418047&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2016.04.047

DO - 10.1016/j.procs.2016.04.047

M3 - Conference article

AN - SCOPUS:84976418047

SN - 1877-0509

VL - 81

SP - 182

EP - 187

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 5th Workshop on Spoken Language Technologies for Under-resourced languages, SLTU 2016

Y2 - 9 May 2016 through 12 May 2016

ER -

Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this