Institut for Forretningsudvikling og Teknologi

Ramjee Prasad

Frame Selection for Robust Speaker Identification: A Hybrid Approach

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Standard

Frame Selection for Robust Speaker Identification : A Hybrid Approach. / Prasad, Swati; Tan, Zheng Hua; Prasad, Ramjee.

I: Wireless Personal Communications, Bind 97, Nr. 1, 01.11.2017, s. 933-950.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Harvard

Prasad, S, Tan, ZH & Prasad, R 2017, 'Frame Selection for Robust Speaker Identification: A Hybrid Approach', Wireless Personal Communications, bind 97, nr. 1, s. 933-950. https://doi.org/10.1007/s11277-017-4544-1

APA

Prasad, S., Tan, Z. H., & Prasad, R. (2017). Frame Selection for Robust Speaker Identification: A Hybrid Approach. Wireless Personal Communications, 97(1), 933-950. https://doi.org/10.1007/s11277-017-4544-1

CBE

MLA

Prasad, Swati, Zheng Hua Tan, og Ramjee Prasad. "Frame Selection for Robust Speaker Identification: A Hybrid Approach". Wireless Personal Communications. 2017, 97(1). 933-950. https://doi.org/10.1007/s11277-017-4544-1

Vancouver

Prasad S, Tan ZH, Prasad R. Frame Selection for Robust Speaker Identification: A Hybrid Approach. Wireless Personal Communications. 2017 nov 1;97(1):933-950. https://doi.org/10.1007/s11277-017-4544-1

Author

Prasad, Swati ; Tan, Zheng Hua ; Prasad, Ramjee. / Frame Selection for Robust Speaker Identification : A Hybrid Approach. I: Wireless Personal Communications. 2017 ; Bind 97, Nr. 1. s. 933-950.

Bibtex

@article{c539f9a0c5cc4564aceec4531ce039e9,
title = "Frame Selection for Robust Speaker Identification: A Hybrid Approach",
abstract = "Identification of a person using voice is a challenging task under environmental noises. Important and reliable frame selection for feature extraction from the time-domain speech signal under noise can play a significant role in improving speaker identification accuracy. Therefore, this paper presents a frame selection method using hybrid technique, which combines two techniques, namely, voice activity detection (VAD) and variable frame rate (VFR) analysis. It efficiently captures the active speech part, the changes in the temporal characteristics of the speech signal, taking into account the signal-to-noise ratio, and thereby speaker-specific information. Experimental results on noisy speech, generated by artificially adding various noise signals to the clean YOHO speech at different SNRs have shown improved results for the frame selection by the hybrid technique in comparison with any one of the techniques used for the hybrid. The proposed hybrid technique outperformed both the VFR and the widely used Gaussian statistical model based VAD method for all noise scenarios at different SNRs, except for the Babble noise corrupted speech at 5 dB SNR, for which, VFR performed better. Considering the average identification accuracies of different noise scenarios, a relative improvement of 9.79{\%} over the VFR, and 18.05{\%} over the Gaussian statistical model based VAD method has been achieved.",
keywords = "Biometric, Frame selection, Robust speaker identification, Variable frame rate (VFR)",
author = "Swati Prasad and Tan, {Zheng Hua} and Ramjee Prasad",
year = "2017",
month = "11",
day = "1",
doi = "10.1007/s11277-017-4544-1",
language = "English",
volume = "97",
pages = "933--950",
journal = "Wireless Personal Communications",
issn = "0929-6212",
publisher = "Springer New York LLC",
number = "1",

}

RIS

TY - JOUR

T1 - Frame Selection for Robust Speaker Identification

T2 - A Hybrid Approach

AU - Prasad, Swati

AU - Tan, Zheng Hua

AU - Prasad, Ramjee

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Identification of a person using voice is a challenging task under environmental noises. Important and reliable frame selection for feature extraction from the time-domain speech signal under noise can play a significant role in improving speaker identification accuracy. Therefore, this paper presents a frame selection method using hybrid technique, which combines two techniques, namely, voice activity detection (VAD) and variable frame rate (VFR) analysis. It efficiently captures the active speech part, the changes in the temporal characteristics of the speech signal, taking into account the signal-to-noise ratio, and thereby speaker-specific information. Experimental results on noisy speech, generated by artificially adding various noise signals to the clean YOHO speech at different SNRs have shown improved results for the frame selection by the hybrid technique in comparison with any one of the techniques used for the hybrid. The proposed hybrid technique outperformed both the VFR and the widely used Gaussian statistical model based VAD method for all noise scenarios at different SNRs, except for the Babble noise corrupted speech at 5 dB SNR, for which, VFR performed better. Considering the average identification accuracies of different noise scenarios, a relative improvement of 9.79% over the VFR, and 18.05% over the Gaussian statistical model based VAD method has been achieved.

AB - Identification of a person using voice is a challenging task under environmental noises. Important and reliable frame selection for feature extraction from the time-domain speech signal under noise can play a significant role in improving speaker identification accuracy. Therefore, this paper presents a frame selection method using hybrid technique, which combines two techniques, namely, voice activity detection (VAD) and variable frame rate (VFR) analysis. It efficiently captures the active speech part, the changes in the temporal characteristics of the speech signal, taking into account the signal-to-noise ratio, and thereby speaker-specific information. Experimental results on noisy speech, generated by artificially adding various noise signals to the clean YOHO speech at different SNRs have shown improved results for the frame selection by the hybrid technique in comparison with any one of the techniques used for the hybrid. The proposed hybrid technique outperformed both the VFR and the widely used Gaussian statistical model based VAD method for all noise scenarios at different SNRs, except for the Babble noise corrupted speech at 5 dB SNR, for which, VFR performed better. Considering the average identification accuracies of different noise scenarios, a relative improvement of 9.79% over the VFR, and 18.05% over the Gaussian statistical model based VAD method has been achieved.

KW - Biometric

KW - Frame selection

KW - Robust speaker identification

KW - Variable frame rate (VFR)

UR - http://www.scopus.com/inward/record.url?scp=85019683611&partnerID=8YFLogxK

U2 - 10.1007/s11277-017-4544-1

DO - 10.1007/s11277-017-4544-1

M3 - Journal article

VL - 97

SP - 933

EP - 950

JO - Wireless Personal Communications

JF - Wireless Personal Communications

SN - 0929-6212

IS - 1

ER -