Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification

Chunyan LIANG; Lin YANG; Qingwei ZHAO; Yonghong YAN

doi:10.1587/transinf.E95.D.2572

Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification

Chunyan LIANG, Lin YANG, Qingwei ZHAO, Yonghong YAN

Full Text Views

0

Share
Cite this

Summary :

In this letter, we adopt a new factor analysis of neighborhood-preserving embedding (NPE) for speaker verification. NPE aims at preserving the local neighborhood structure on the data and defines a low-dimensional speaker space called neighborhood-preserving embedding space. We compare the proposed method with the state-of-the-art total variability approach on the telephone-telephone core condition of the NIST 2008 Speaker Recognition Evaluation (SRE) dataset. The experimental results indicate that the proposed NPE method outperforms the total variability approach, providing up to 24% relative improvement.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.10 pp.2572-2576

Publication Date: 2012/10/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.2572

Type of Manuscript: LETTER

Category: Speech and Hearing

Cite this

Copy

Chunyan LIANG, Lin YANG, Qingwei ZHAO, Yonghong YAN, "Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 10, pp. 2572-2576, October 2012, doi: 10.1587/transinf.E95.D.2572.
Abstract: In this letter, we adopt a new factor analysis of neighborhood-preserving embedding (NPE) for speaker verification. NPE aims at preserving the local neighborhood structure on the data and defines a low-dimensional speaker space called neighborhood-preserving embedding space. We compare the proposed method with the state-of-the-art total variability approach on the telephone-telephone core condition of the NIST 2008 Speaker Recognition Evaluation (SRE) dataset. The experimental results indicate that the proposed NPE method outperforms the total variability approach, providing up to 24% relative improvement.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E95.D.2572/_p

Copy

@ARTICLE{e95-d_10_2572,
author={Chunyan LIANG, Lin YANG, Qingwei ZHAO, Yonghong YAN, },
journal={IEICE TRANSACTIONS on Information},
title={Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification},
year={2012},
volume={E95-D},
number={10},
pages={2572-2576},
abstract={In this letter, we adopt a new factor analysis of neighborhood-preserving embedding (NPE) for speaker verification. NPE aims at preserving the local neighborhood structure on the data and defines a low-dimensional speaker space called neighborhood-preserving embedding space. We compare the proposed method with the state-of-the-art total variability approach on the telephone-telephone core condition of the NIST 2008 Speaker Recognition Evaluation (SRE) dataset. The experimental results indicate that the proposed NPE method outperforms the total variability approach, providing up to 24% relative improvement.},
keywords={},
doi={10.1587/transinf.E95.D.2572},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification
T2 - IEICE TRANSACTIONS on Information
SP - 2572
EP - 2576
AU - Chunyan LIANG
AU - Lin YANG
AU - Qingwei ZHAO
AU - Yonghong YAN
PY - 2012
DO - 10.1587/transinf.E95.D.2572
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2012
AB - In this letter, we adopt a new factor analysis of neighborhood-preserving embedding (NPE) for speaker verification. NPE aims at preserving the local neighborhood structure on the data and defines a low-dimensional speaker space called neighborhood-preserving embedding space. We compare the proposed method with the state-of-the-art total variability approach on the telephone-telephone core condition of the NIST 2008 Speaker Recognition Evaluation (SRE) dataset. The experimental results indicate that the proposed NPE method outperforms the total variability approach, providing up to 24% relative improvement.
ER -