Robust statistical-based speaker's location detection algorithm in a vehicular environment

Jwu-Sheng Hu; Chieh-Cheng Cheng; Wei-Han Liu; Chia Hsing Yang

Robust statistical-based speaker's location detection algorithm in a vehicular environment

Jwu-Sheng Hu, Chieh-Cheng Cheng, Wei-Han Liu, Chia Hsing Yang

National Chiao Tung University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This work proposes a threshold adaptation method to detect speaker's location in a vehicular environment. The method is robust to unmodeled sound source locations in a noisy environment and uses a single linear microphone array. The proposed approach is an improvement over previous work [12] which adopts Gaussian mixture models (GMMs) to model location-dependent but content and speaker independent acoustic characteristics of sound sources. Experimental results show that this scheme can overcome the far-filed and near-riled problem with the same architecture and perform well in both line-of-sight and non-line-of-sight cases.

Original language	English
Title of host publication	2006 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING, VOLS 1 AND 2
Publisher	IEEE
Pages	274-+
ISBN (Print)	978-1-4244-0310-3
State	Published - 8 Oct 2006

Keywords

Microphone array
sound locatization
GMM
HCI

Fingerprint Dive into the research topics of 'Robust statistical-based speaker's location detection algorithm in a vehicular environment'. Together they form a unique fingerprint.

Cite this

@inproceedings{aa7e0844260d4e37925121fbdb67cbac,

title = "Robust statistical-based speaker's location detection algorithm in a vehicular environment",

abstract = "This work proposes a threshold adaptation method to detect speaker's location in a vehicular environment. The method is robust to unmodeled sound source locations in a noisy environment and uses a single linear microphone array. The proposed approach is an improvement over previous work [12] which adopts Gaussian mixture models (GMMs) to model location-dependent but content and speaker independent acoustic characteristics of sound sources. Experimental results show that this scheme can overcome the far-filed and near-riled problem with the same architecture and perform well in both line-of-sight and non-line-of-sight cases.",

keywords = "Microphone array, sound locatization, GMM, HCI",

author = "Jwu-Sheng Hu and Chieh-Cheng Cheng and Wei-Han Liu and Yang, {Chia Hsing}",

year = "2006",

month = oct,

day = "8",

language = "English",

isbn = "978-1-4244-0310-3",

pages = "274--+",

booktitle = "2006 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING, VOLS 1 AND 2",

publisher = "IEEE",

}

Robust statistical-based speaker's location detection algorithm in a vehicular environment. / Hu, Jwu-Sheng; Cheng, Chieh-Cheng; Liu, Wei-Han; Yang, Chia Hsing.

2006 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING, VOLS 1 AND 2. IEEE, 2006. p. 274-+.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Robust statistical-based speaker's location detection algorithm in a vehicular environment

AU - Hu, Jwu-Sheng

AU - Cheng, Chieh-Cheng

AU - Liu, Wei-Han

AU - Yang, Chia Hsing

PY - 2006/10/8

Y1 - 2006/10/8

N2 - This work proposes a threshold adaptation method to detect speaker's location in a vehicular environment. The method is robust to unmodeled sound source locations in a noisy environment and uses a single linear microphone array. The proposed approach is an improvement over previous work [12] which adopts Gaussian mixture models (GMMs) to model location-dependent but content and speaker independent acoustic characteristics of sound sources. Experimental results show that this scheme can overcome the far-filed and near-riled problem with the same architecture and perform well in both line-of-sight and non-line-of-sight cases.

AB - This work proposes a threshold adaptation method to detect speaker's location in a vehicular environment. The method is robust to unmodeled sound source locations in a noisy environment and uses a single linear microphone array. The proposed approach is an improvement over previous work [12] which adopts Gaussian mixture models (GMMs) to model location-dependent but content and speaker independent acoustic characteristics of sound sources. Experimental results show that this scheme can overcome the far-filed and near-riled problem with the same architecture and perform well in both line-of-sight and non-line-of-sight cases.

KW - Microphone array

KW - sound locatization

KW - GMM

KW - HCI

M3 - Conference contribution

SN - 978-1-4244-0310-3

SP - 274-+

BT - 2006 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING, VOLS 1 AND 2

PB - IEEE

ER -