Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION

Abstract: 

In this paper we focus on the usefulness of verbal events for speech based emotion recognition. In particular, the use of phoneme sequences to encode verbal cues related to the expression of emotions is proposed and lexical features based on these phoneme sequences are introduced for use in automatic emotion recognition systems where manual transcripts are not available. Secondly, a novel estimate of emotional salience of verbal cues, applicable to both phoneme sequences and words, is presented. Experimental results on the IEMOCAP database show that the proposed automatic phoneme sequence based features can achieve an Unweighted Average Recall (UAR) of 49.9% with proposed salience measure. Further, the proposed salience measure can lead to an UAR of 64% when using manual word transcriptions. Both of these are the highest UARs reported on the IEMOCAP database for systems using lexical features extracted from automatic and manual transcripts respectively.

Index Terms— speech based emotion recognition, human-computer interactions, lexical features, emotional salience

up
0 users have voted:

Paper Details

Authors:
Kalani Wataraka Gamage, Vidhyasaharan Sethu, Eliathamby Ambikairajah
Submitted On:
3 August 2017 - 3:55am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Kalani Wataraka Gamage
Paper Code:
2375
Document Year:
2017
Cite

Document Files

http://ieeexplore.ieee.org/document/7953274/

(13 downloads)

Subscribe

[1] Kalani Wataraka Gamage, Vidhyasaharan Sethu, Eliathamby Ambikairajah, "SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1800. Accessed: Aug. 18, 2017.
@article{1800-17,
url = {http://sigport.org/1800},
author = {Kalani Wataraka Gamage; Vidhyasaharan Sethu; Eliathamby Ambikairajah },
publisher = {IEEE SigPort},
title = {SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION},
year = {2017} }
TY - EJOUR
T1 - SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION
AU - Kalani Wataraka Gamage; Vidhyasaharan Sethu; Eliathamby Ambikairajah
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1800
ER -
Kalani Wataraka Gamage, Vidhyasaharan Sethu, Eliathamby Ambikairajah. (2017). SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION. IEEE SigPort. http://sigport.org/1800
Kalani Wataraka Gamage, Vidhyasaharan Sethu, Eliathamby Ambikairajah, 2017. SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION. Available at: http://sigport.org/1800.
Kalani Wataraka Gamage, Vidhyasaharan Sethu, Eliathamby Ambikairajah. (2017). "SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION." Web.
1. Kalani Wataraka Gamage, Vidhyasaharan Sethu, Eliathamby Ambikairajah. SALIENCE BASED LEXICAL FEATURES FOR EMOTION RECOGNITION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1800