Automatic Language Identification with Discriminative Language Characterization Based on SVM

Hongbin SUO; Ming LI; Ping LU; Yonghong YAN

doi:10.1093/ietisy/e91-d.3.567

Automatic Language Identification with Discriminative Language Characterization Based on SVM

Hongbin SUO, Ming LI, Ping LU, Yonghong YAN

Full Text Views

0

Share
Cite this

Summary :

Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by classifiers. In this paper, in order to increase the dimension of the score vector and alleviate the inter-speaker variability within the same language, multiple data groups based on supervised speaker clustering are employed to generate the discriminative language characterization score vectors (DLCSV). The back-end SVM classifiers are used to model the probability distribution of each target language in the DLCSV space. Finally, the output scores of back-end classifiers are calibrated by a pair-wise posterior probability estimation (PPPE) algorithm. The proposed language identification frameworks are evaluated on 2003 NIST Language Recognition Evaluation (LRE) databases and the experiments show that the system described in this paper produces comparable results to the existing systems. Especially, the SVM framework achieves an equal error rate (EER) of 4.0% in the 30-second task and outperforms the state-of-art systems by more than 30% relative error reduction. Besides, the performances of proposed PPRLM and GMMs algorithms achieve an EER of 5.1% and 5.0% respectively.

Publication: IEICE TRANSACTIONS on Information Vol.E91-D No.3 pp.567-575

Publication Date: 2008/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e91-d.3.567

Type of Manuscript: Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)

Category: Language Identification

Cite this

Copy

Hongbin SUO, Ming LI, Ping LU, Yonghong YAN, "Automatic Language Identification with Discriminative Language Characterization Based on SVM" in IEICE TRANSACTIONS on Information, vol. E91-D, no. 3, pp. 567-575, March 2008, doi: 10.1093/ietisy/e91-d.3.567.
Abstract: Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by classifiers. In this paper, in order to increase the dimension of the score vector and alleviate the inter-speaker variability within the same language, multiple data groups based on supervised speaker clustering are employed to generate the discriminative language characterization score vectors (DLCSV). The back-end SVM classifiers are used to model the probability distribution of each target language in the DLCSV space. Finally, the output scores of back-end classifiers are calibrated by a pair-wise posterior probability estimation (PPPE) algorithm. The proposed language identification frameworks are evaluated on 2003 NIST Language Recognition Evaluation (LRE) databases and the experiments show that the system described in this paper produces comparable results to the existing systems. Especially, the SVM framework achieves an equal error rate (EER) of 4.0% in the 30-second task and outperforms the state-of-art systems by more than 30% relative error reduction. Besides, the performances of proposed PPRLM and GMMs algorithms achieve an EER of 5.1% and 5.0% respectively.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.3.567/_p

Copy

@ARTICLE{e91-d_3_567,
author={Hongbin SUO, Ming LI, Ping LU, Yonghong YAN, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Language Identification with Discriminative Language Characterization Based on SVM},
year={2008},
volume={E91-D},
number={3},
pages={567-575},
abstract={Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by classifiers. In this paper, in order to increase the dimension of the score vector and alleviate the inter-speaker variability within the same language, multiple data groups based on supervised speaker clustering are employed to generate the discriminative language characterization score vectors (DLCSV). The back-end SVM classifiers are used to model the probability distribution of each target language in the DLCSV space. Finally, the output scores of back-end classifiers are calibrated by a pair-wise posterior probability estimation (PPPE) algorithm. The proposed language identification frameworks are evaluated on 2003 NIST Language Recognition Evaluation (LRE) databases and the experiments show that the system described in this paper produces comparable results to the existing systems. Especially, the SVM framework achieves an equal error rate (EER) of 4.0% in the 30-second task and outperforms the state-of-art systems by more than 30% relative error reduction. Besides, the performances of proposed PPRLM and GMMs algorithms achieve an EER of 5.1% and 5.0% respectively.},
keywords={},
doi={10.1093/ietisy/e91-d.3.567},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Automatic Language Identification with Discriminative Language Characterization Based on SVM
T2 - IEICE TRANSACTIONS on Information
SP - 567
EP - 575
AU - Hongbin SUO
AU - Ming LI
AU - Ping LU
AU - Yonghong YAN
PY - 2008
DO - 10.1093/ietisy/e91-d.3.567
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2008
AB - Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by classifiers. In this paper, in order to increase the dimension of the score vector and alleviate the inter-speaker variability within the same language, multiple data groups based on supervised speaker clustering are employed to generate the discriminative language characterization score vectors (DLCSV). The back-end SVM classifiers are used to model the probability distribution of each target language in the DLCSV space. Finally, the output scores of back-end classifiers are calibrated by a pair-wise posterior probability estimation (PPPE) algorithm. The proposed language identification frameworks are evaluated on 2003 NIST Language Recognition Evaluation (LRE) databases and the experiments show that the system described in this paper produces comparable results to the existing systems. Especially, the SVM framework achieves an equal error rate (EER) of 4.0% in the 30-second task and outperforms the state-of-art systems by more than 30% relative error reduction. Besides, the performances of proposed PPRLM and GMMs algorithms achieve an EER of 5.1% and 5.0% respectively.
ER -