Publication

Multimodal emotion recognition for AVEC 2016 challenge

Povolny, Filip
; 
Matejka, Pavel
; 
Hradis, Michal
; 
Popkova, Anna
; 
Otrusina, Lubomir
; 
Smrz, Pavel
; 
Wood, Ian
; 
Robin, Cécile
; 
Lamel, Lori
Thumbnail Image
Files
Thumbnail Image
Povolny_et_al_-_2016_-_Multimodal_Emotion_Recognition_for_AVEC_2016_Challenge.pdf
Adobe PDF, 931.83 KB
Identifiers
http://hdl.handle.net/10379/7036
 https://doi.org/10.13025/20997
Publication Date
2016-10-16
Keywords
Emotion recognition, Valence, Arousal, Bottleneck features, Neural networks, Regression, Speech transcription, Word embedding
Type
Conference Paper
Downloads
Show all metadata
Citation
Povolny, Filip, Matejka, Pavel, Hradis, Michal, Popkov, Anna, Otrusina, Lubomir, Smrz, PaveL, Wood, Ian, Robin, Cécile, Lamel, Lori. (2016). Multimodal Emotion Recognition for AVEC 2016 Challenge. Paper presented at the Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge, Amsterdam, The Netherlands.
Abstract
This paper describes a systems for emotion recognition and its application on the dataset from the AV+EC 2016 Emotion Recognition Challenge. The realized system was produced and submitted to the AV+EC 2016 evaluation, making use of all three modalities (audio, video, and physiological data). Our work primarily focused on features derived from audio. The original audio features were complement with bottleneck features and also text-based emotion recognition which is based on transcribing audio by an automatic speech recognition system and applying resources such as word embedding models and sentiment lexicons. Our multimodal fusion reached CCC=0.855 on dev set for arousal and 0.713 for valence. CCC on test set is 0.719 and 0.596 for arousal and valence respectively.
Funder
EU Horizon 2020
Publisher
ACM
Publisher DOI
Rights
Attribution-NonCommercial-NoDerivs 3.0 Ireland
cbn
Collections
Data Science Institute (Conference Papers)