Influence of speakers' emotional states on voice recognition scores

Authors:
Piotr Staroniewicz
Affiliations:
Institute of Telecommunications, Teleinformatics and Acoustics, Wroclaw University of Technology, Wroclaw, Poland
Venue:
COST'10 Proceedings of the 2010 international conference on Analysis of Verbal and Nonverbal Communication and Enactment
Year:
2010

Citing 4
Cited 0

Emotional speech: towards a new generation of databases

Speech Communication - Special issue on speech and emotion
A tutorial on text-independent speaker verification

EURASIP Journal on Applied Signal Processing
Polish Emotional Speech Database --- Recording and Preliminary Validation

Cross-Modal Analysis of Speech, Gestures, Gaze and Facial Expressions
Recognition of emotional state in Polish speech: comparison between human and automatic efficiency

BioID_MultiComm'09 Proceedings of the 2009 joint COST 2101 and 2102 international conference on Biometric ID management and multimodal communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper presents the voice recognition EER (Equal Error Rate) scores for speakers' basic emotional states. The database of Polish emotional speech used during the tests includes recordings of six acted emotional states (anger, sadness, happiness, fear, disgusts, surprise) and the neutral state of 13 amateur speakers (2118 utterances). The voice recognition procedure was proceeded with MFCC features and GMM classifiers. The EER scores distinctly depend on speakers' emotional states, even for a simulated database. The mean EER results tend to be only slightly less sensitive to an emotional state, even when using speech in various kinds of emotional arousal in a training set.