TY - JOUR
T1 - Investigating the visual lombard effect with gabor based features
AU - Chiu, Waito
AU - Xu, Yan
AU - Abel, Andrew
AU - Lin, Chun
AU - Tu, Zhengzheng
N1 - Funding Information: This data was recorded as part of a Nuffield Trust Research Placement at the University of Stirling, Scotland. The authors would like to especially thank Dawn Hearsum for her hard work with data collection, and we would also like to thank Professor Roger Watt and Professor Leslie Smith for their advice.
Publisher Copyright: Copyright © 2020 ISCA
Cite as: Chiu, W., Xu, Y., Abel, A., Lin, C., Tu, Z. (2020) Investigating the Visual Lombard Effect with Gabor Based Features. Proc. Interspeech 2020, 4606-4610, doi: 10.21437/Interspeech.2020-1291
PY - 2020/10/29
Y1 - 2020/10/29
N2 - The Lombard Effect shows that speakers increase their vocal effort in the presence of noise, and research into acoustic speech, has demonstrated varying effects, depending on the noise level and speaker, with several differences, including timing and vocal effort. Research also identified several differences, including between gender, and noise type. However, most research has focused on the audio domain, with very limited focus on the visual effect. This paper presents a detailed study of the visual Lombard Effect, using a pilot Lombard Speech corpus developed for our needs, and a recently developed Gabor based lip feature extraction approach. Using Kernel Density Estimation, we identify clear differences between genders, and also show that speakers handle different noise types differently.
AB - The Lombard Effect shows that speakers increase their vocal effort in the presence of noise, and research into acoustic speech, has demonstrated varying effects, depending on the noise level and speaker, with several differences, including timing and vocal effort. Research also identified several differences, including between gender, and noise type. However, most research has focused on the audio domain, with very limited focus on the visual effect. This paper presents a detailed study of the visual Lombard Effect, using a pilot Lombard Speech corpus developed for our needs, and a recently developed Gabor based lip feature extraction approach. Using Kernel Density Estimation, we identify clear differences between genders, and also show that speakers handle different noise types differently.
KW - Gabor Features
KW - lip Features
KW - lombard Effect
KW - vocal effort
KW - acoustic speech
KW - noise
UR - http://www.scopus.com/inward/record.url?scp=85098112563&partnerID=8YFLogxK
U2 - 10.21437/Interspeech.2020-1291
DO - 10.21437/Interspeech.2020-1291
M3 - Conference article
AN - SCOPUS:85098112563
SN - 2308-457X
VL - 2020-October
SP - 4606
EP - 4610
JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
T2 - 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020
Y2 - 25 October 2020 through 29 October 2020
ER -