Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using <I>F</I><SUB>0</SUB> Information

Taichi ASAMI; Koji IWANO; Sadaoki FURUI

doi:10.1093/ietisy/e91-d.3.549

Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using F₀ Information

Taichi ASAMI, Koji IWANO, Sadaoki FURUI

Full Text Views

0

Share
Cite this

Summary :

We have previously proposed a noise-robust speaker verification method using fundamental frequency (F₀) extracted using the Hough transform. The method also incorporates an automatic stream-weight and decision threshold estimation technique. It has been confirmed that the proposed method is effective for white noise at various SNR conditions. This paper evaluates the proposed method in more practical in-car and elevator-hall noise conditions. The paper first describes the noise-robust F₀ extraction method and details of our robust speaker verification method using multi-stream HMMs for integrating the extracted F₀ and cepstral features. Details of the automatic stream-weight and threshold estimation method for multi-stream speaker verification framework are also explained. This method simultaneously optimizes stream-weights and a decision threshold by combining the linear discriminant analysis (LDA) and the Adaboost technique. Experiments were conducted using Japanese connected digit speech contaminated by white, in-car, or elevator-hall noise at various SNRs. Experimental results show that the F₀ features improve the verification performance in various noisy environments, and that our stream-weight and threshold optimization method effectively estimates control parameters so that FARs and FRRs are adjusted to achieve equal error rates (EERs) under various noisy conditions.

Publication: IEICE TRANSACTIONS on Information Vol.E91-D No.3 pp.549-557

Publication Date: 2008/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e91-d.3.549

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

Category: Speaker Verification

Cite this

Copy

Taichi ASAMI, Koji IWANO, Sadaoki FURUI, "Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using F0 Information" in IEICE TRANSACTIONS on Information, vol. E91-D, no. 3, pp. 549-557, March 2008, doi: 10.1093/ietisy/e91-d.3.549.
Abstract: We have previously proposed a noise-robust speaker verification method using fundamental frequency (F₀) extracted using the Hough transform. The method also incorporates an automatic stream-weight and decision threshold estimation technique. It has been confirmed that the proposed method is effective for white noise at various SNR conditions. This paper evaluates the proposed method in more practical in-car and elevator-hall noise conditions. The paper first describes the noise-robust F₀ extraction method and details of our robust speaker verification method using multi-stream HMMs for integrating the extracted F₀ and cepstral features. Details of the automatic stream-weight and threshold estimation method for multi-stream speaker verification framework are also explained. This method simultaneously optimizes stream-weights and a decision threshold by combining the linear discriminant analysis (LDA) and the Adaboost technique. Experiments were conducted using Japanese connected digit speech contaminated by white, in-car, or elevator-hall noise at various SNRs. Experimental results show that the F₀ features improve the verification performance in various noisy environments, and that our stream-weight and threshold optimization method effectively estimates control parameters so that FARs and FRRs are adjusted to achieve equal error rates (EERs) under various noisy conditions.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.3.549/_p

Copy

@ARTICLE{e91-d_3_549,
author={Taichi ASAMI, Koji IWANO, Sadaoki FURUI, },
journal={IEICE TRANSACTIONS on Information},
title={Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using F0 Information},
year={2008},
volume={E91-D},
number={3},
pages={549-557},
abstract={We have previously proposed a noise-robust speaker verification method using fundamental frequency (F₀) extracted using the Hough transform. The method also incorporates an automatic stream-weight and decision threshold estimation technique. It has been confirmed that the proposed method is effective for white noise at various SNR conditions. This paper evaluates the proposed method in more practical in-car and elevator-hall noise conditions. The paper first describes the noise-robust F₀ extraction method and details of our robust speaker verification method using multi-stream HMMs for integrating the extracted F₀ and cepstral features. Details of the automatic stream-weight and threshold estimation method for multi-stream speaker verification framework are also explained. This method simultaneously optimizes stream-weights and a decision threshold by combining the linear discriminant analysis (LDA) and the Adaboost technique. Experiments were conducted using Japanese connected digit speech contaminated by white, in-car, or elevator-hall noise at various SNRs. Experimental results show that the F₀ features improve the verification performance in various noisy environments, and that our stream-weight and threshold optimization method effectively estimates control parameters so that FARs and FRRs are adjusted to achieve equal error rates (EERs) under various noisy conditions.},
keywords={},
doi={10.1093/ietisy/e91-d.3.549},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using F0 Information
T2 - IEICE TRANSACTIONS on Information
SP - 549
EP - 557
AU - Taichi ASAMI
AU - Koji IWANO
AU - Sadaoki FURUI
PY - 2008
DO - 10.1093/ietisy/e91-d.3.549
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2008
AB - We have previously proposed a noise-robust speaker verification method using fundamental frequency (F₀) extracted using the Hough transform. The method also incorporates an automatic stream-weight and decision threshold estimation technique. It has been confirmed that the proposed method is effective for white noise at various SNR conditions. This paper evaluates the proposed method in more practical in-car and elevator-hall noise conditions. The paper first describes the noise-robust F₀ extraction method and details of our robust speaker verification method using multi-stream HMMs for integrating the extracted F₀ and cepstral features. Details of the automatic stream-weight and threshold estimation method for multi-stream speaker verification framework are also explained. This method simultaneously optimizes stream-weights and a decision threshold by combining the linear discriminant analysis (LDA) and the Adaboost technique. Experiments were conducted using Japanese connected digit speech contaminated by white, in-car, or elevator-hall noise at various SNRs. Experimental results show that the F₀ features improve the verification performance in various noisy environments, and that our stream-weight and threshold optimization method effectively estimates control parameters so that FARs and FRRs are adjusted to achieve equal error rates (EERs) under various noisy conditions.
ER -