Nist 2007 language recognition evaluation: From the perspective of IIR

Haizhou Li; Bin Ma; Kong Aik Lee; Khe Chai Sim; Hanwu Sun; Rong Tong; Donglai Zhu; Changhuai You

Nist 2007 language recognition evaluation: From the perspective of IIR

Haizhou Li
, Bin Ma
, Kong Aik Lee
, Khe Chai Sim
, Hanwu Sun
, Rong Tong
, Donglai Zhu
, Changhuai You

Research output: Unpublished conference presentation (presented paper, abstract, poster) › Conference presentation (not published in journal/proceeding/book) › Academic research › peer-review

1 Citation (Scopus)

Abstract

This paper describes the Institute for Infocomm Research (IIR) system for the 2007 Language Recognition Evaluation (LRE) conducted by the National Institute of Standards and Technology (NIST). The submitted system is a fusion of multiple state-ofthe- art language classifiers using diversified discriminative language cues. We implemented several state-of-the-art algorithms using both phonotactic and acoustic features. We also investigated the system fusion and score calibration strategy to improve the performance of language recognition, and worked out a pseudo-key analysis approach to cross-validate the performance of the individual classifiers on the evaluation data. We achieve an equal-error-rate (EER) of 1.67 % on the close-set general language recognition test.

Original language	English
Pages	46-57
Number of pages	12
Publication status	Published - Nov 2008
Externally published	Yes
Event	22nd Pacific Asia Conference on Language, Information and Computation, PACLIC 22 - Cebu, Philippines Duration: 20 Nov 2008 → 22 Nov 2008

Conference

Conference	22nd Pacific Asia Conference on Language, Information and Computation, PACLIC 22
Country/Territory	Philippines
City	Cebu
Period	20/11/08 → 22/11/08

Keywords

Acoustic features
Automatic spoken language recognition
Fusion system
NIST language recognition evaluation
Phonotactic features
Pseudo key

ASJC Scopus subject areas

Language and Linguistics
Computer Science (miscellaneous)
Information Systems

Cite this

@conference{f1967dfe3ad34d5286221b8c5b5786d0,

title = "Nist 2007 language recognition evaluation: From the perspective of IIR",

abstract = "This paper describes the Institute for Infocomm Research (IIR) system for the 2007 Language Recognition Evaluation (LRE) conducted by the National Institute of Standards and Technology (NIST). The submitted system is a fusion of multiple state-ofthe- art language classifiers using diversified discriminative language cues. We implemented several state-of-the-art algorithms using both phonotactic and acoustic features. We also investigated the system fusion and score calibration strategy to improve the performance of language recognition, and worked out a pseudo-key analysis approach to cross-validate the performance of the individual classifiers on the evaluation data. We achieve an equal-error-rate (EER) of 1.67 \% on the close-set general language recognition test.",

keywords = "Acoustic features, Automatic spoken language recognition, Fusion system, NIST language recognition evaluation, Phonotactic features, Pseudo key",

author = "Haizhou Li and Bin Ma and Lee, \{Kong Aik\} and Sim, \{Khe Chai\} and Hanwu Sun and Rong Tong and Donglai Zhu and Changhuai You",

year = "2008",

month = nov,

language = "English",

pages = "46--57",

note = "22nd Pacific Asia Conference on Language, Information and Computation, PACLIC 22 ; Conference date: 20-11-2008 Through 22-11-2008",

}

Nist 2007 language recognition evaluation: From the perspective of IIR. / Li, Haizhou; Ma, Bin; Lee, Kong Aik et al.
2008. 46-57 Paper presented at 22nd Pacific Asia Conference on Language, Information and Computation, PACLIC 22, Cebu, Philippines.

Research output: Unpublished conference presentation (presented paper, abstract, poster) › Conference presentation (not published in journal/proceeding/book) › Academic research › peer-review

TY - CONF

T1 - Nist 2007 language recognition evaluation: From the perspective of IIR

AU - Li, Haizhou

AU - Ma, Bin

AU - Lee, Kong Aik

AU - Sim, Khe Chai

AU - Sun, Hanwu

AU - Tong, Rong

AU - Zhu, Donglai

AU - You, Changhuai

PY - 2008/11

Y1 - 2008/11

N2 - This paper describes the Institute for Infocomm Research (IIR) system for the 2007 Language Recognition Evaluation (LRE) conducted by the National Institute of Standards and Technology (NIST). The submitted system is a fusion of multiple state-ofthe- art language classifiers using diversified discriminative language cues. We implemented several state-of-the-art algorithms using both phonotactic and acoustic features. We also investigated the system fusion and score calibration strategy to improve the performance of language recognition, and worked out a pseudo-key analysis approach to cross-validate the performance of the individual classifiers on the evaluation data. We achieve an equal-error-rate (EER) of 1.67 % on the close-set general language recognition test.

AB - This paper describes the Institute for Infocomm Research (IIR) system for the 2007 Language Recognition Evaluation (LRE) conducted by the National Institute of Standards and Technology (NIST). The submitted system is a fusion of multiple state-ofthe- art language classifiers using diversified discriminative language cues. We implemented several state-of-the-art algorithms using both phonotactic and acoustic features. We also investigated the system fusion and score calibration strategy to improve the performance of language recognition, and worked out a pseudo-key analysis approach to cross-validate the performance of the individual classifiers on the evaluation data. We achieve an equal-error-rate (EER) of 1.67 % on the close-set general language recognition test.

KW - Acoustic features

KW - Automatic spoken language recognition

KW - Fusion system

KW - NIST language recognition evaluation

KW - Phonotactic features

KW - Pseudo key

UR - https://www.scopus.com/pages/publications/68549091552

M3 - Conference presentation (not published in journal/proceeding/book)

AN - SCOPUS:68549091552

SP - 46

EP - 57

T2 - 22nd Pacific Asia Conference on Language, Information and Computation, PACLIC 22

Y2 - 20 November 2008 through 22 November 2008

ER -

Nist 2007 language recognition evaluation: From the perspective of IIR

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this