Robust visual voice activity detection using local variance histogram in vehicular environments

Kyungsun Lee, Taeyup Song, Sungsoo Kim, David K. Han, Hanseok Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a Vision based Voice Activity Detection (VVAD) algorithm is proposed using Local Variance Histogram (LVH). In conventional VVAD algorithm, the motion measure such as optical flow and intensity histogram are widely used. However, this approach is unstable under varying illumination and global motion changes which frequently occur in moving vehicular environment. To mitigate this problem, an appropriate framework based on LVH feature is developed. Comparison with two other conventional visual voice activity detectors shows the proposed method to be consistently more accurate and yields a substantial improvement in terms of detection probability and false alarm rate.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Consumer Electronics, ICCE 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages449-450
Number of pages2
ISBN (Print)9781479975426
DOIs
Publication statusPublished - 2015 Mar 23
Event2015 IEEE International Conference on Consumer Electronics, ICCE 2015 - Las Vegas, United States
Duration: 2015 Jan 92015 Jan 12

Other

Other2015 IEEE International Conference on Consumer Electronics, ICCE 2015
CountryUnited States
CityLas Vegas
Period15/1/915/1/12

Fingerprint

Optical flows
Lighting
Detectors

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Lee, K., Song, T., Kim, S., Han, D. K., & Ko, H. (2015). Robust visual voice activity detection using local variance histogram in vehicular environments. In 2015 IEEE International Conference on Consumer Electronics, ICCE 2015 (pp. 449-450). [7066482] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE.2015.7066482

Robust visual voice activity detection using local variance histogram in vehicular environments. / Lee, Kyungsun; Song, Taeyup; Kim, Sungsoo; Han, David K.; Ko, Hanseok.

2015 IEEE International Conference on Consumer Electronics, ICCE 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 449-450 7066482.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, K, Song, T, Kim, S, Han, DK & Ko, H 2015, Robust visual voice activity detection using local variance histogram in vehicular environments. in 2015 IEEE International Conference on Consumer Electronics, ICCE 2015., 7066482, Institute of Electrical and Electronics Engineers Inc., pp. 449-450, 2015 IEEE International Conference on Consumer Electronics, ICCE 2015, Las Vegas, United States, 15/1/9. https://doi.org/10.1109/ICCE.2015.7066482
Lee K, Song T, Kim S, Han DK, Ko H. Robust visual voice activity detection using local variance histogram in vehicular environments. In 2015 IEEE International Conference on Consumer Electronics, ICCE 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 449-450. 7066482 https://doi.org/10.1109/ICCE.2015.7066482
Lee, Kyungsun ; Song, Taeyup ; Kim, Sungsoo ; Han, David K. ; Ko, Hanseok. / Robust visual voice activity detection using local variance histogram in vehicular environments. 2015 IEEE International Conference on Consumer Electronics, ICCE 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 449-450
@inproceedings{d94859c20484400d8136e42ddb5ec035,
title = "Robust visual voice activity detection using local variance histogram in vehicular environments",
abstract = "In this paper, a Vision based Voice Activity Detection (VVAD) algorithm is proposed using Local Variance Histogram (LVH). In conventional VVAD algorithm, the motion measure such as optical flow and intensity histogram are widely used. However, this approach is unstable under varying illumination and global motion changes which frequently occur in moving vehicular environment. To mitigate this problem, an appropriate framework based on LVH feature is developed. Comparison with two other conventional visual voice activity detectors shows the proposed method to be consistently more accurate and yields a substantial improvement in terms of detection probability and false alarm rate.",
author = "Kyungsun Lee and Taeyup Song and Sungsoo Kim and Han, {David K.} and Hanseok Ko",
year = "2015",
month = "3",
day = "23",
doi = "10.1109/ICCE.2015.7066482",
language = "English",
isbn = "9781479975426",
pages = "449--450",
booktitle = "2015 IEEE International Conference on Consumer Electronics, ICCE 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Robust visual voice activity detection using local variance histogram in vehicular environments

AU - Lee, Kyungsun

AU - Song, Taeyup

AU - Kim, Sungsoo

AU - Han, David K.

AU - Ko, Hanseok

PY - 2015/3/23

Y1 - 2015/3/23

N2 - In this paper, a Vision based Voice Activity Detection (VVAD) algorithm is proposed using Local Variance Histogram (LVH). In conventional VVAD algorithm, the motion measure such as optical flow and intensity histogram are widely used. However, this approach is unstable under varying illumination and global motion changes which frequently occur in moving vehicular environment. To mitigate this problem, an appropriate framework based on LVH feature is developed. Comparison with two other conventional visual voice activity detectors shows the proposed method to be consistently more accurate and yields a substantial improvement in terms of detection probability and false alarm rate.

AB - In this paper, a Vision based Voice Activity Detection (VVAD) algorithm is proposed using Local Variance Histogram (LVH). In conventional VVAD algorithm, the motion measure such as optical flow and intensity histogram are widely used. However, this approach is unstable under varying illumination and global motion changes which frequently occur in moving vehicular environment. To mitigate this problem, an appropriate framework based on LVH feature is developed. Comparison with two other conventional visual voice activity detectors shows the proposed method to be consistently more accurate and yields a substantial improvement in terms of detection probability and false alarm rate.

UR - http://www.scopus.com/inward/record.url?scp=84936117164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936117164&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2015.7066482

DO - 10.1109/ICCE.2015.7066482

M3 - Conference contribution

SN - 9781479975426

SP - 449

EP - 450

BT - 2015 IEEE International Conference on Consumer Electronics, ICCE 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -