Paper Info
Title
The Performance of the Speaking Rate Parameter in Emotion Recognition from Speech
Abstract
The speaking rate is a quite obvious prosodic characteristic of speech and humans can easily estimate how fast an interlocutor is talking. Further, different emotional dispositions of a person are strongly expressed in his/her speaking rate. In this paper we investigate the performance gain originating from the use of the speaking rate parameter in emotion recognition from speech. The speaking rates are determined by applying a broad phonetic class recognizer. The classifier is trained on cepstral features extracted on the emotionally neutral RM1 speech corpus and provides low average recognition errors of one phoneme/second. We present the results of an empirical approach on the emotionally expressive Emo-DB corpus applying a neural network classifier and prove the significant influence of the speaking rate in emotion classification. The performances of Multi-Layer Perceptrons trained on cepstral turn-level features are analyzed with respect to the presence and absence of the speaking rate feature. An increase of accuracy up to 3.7% in certain emotion categories is reported.
Year
DOI
Venue
2012
10.1109/ICME.2012.183
Multimedia and Expo
Keywords
DocType
ISSN
cepstral analysis,emotion recognition,feature extraction,multilayer perceptrons,signal classification,speech recognition,cepstral features extraction,cepstral turn-level features,emotion classification,emotion recognition,emotional expressive Emo-DB corpus,emotional neutral RM1 speech corpus,multilayer perceptrons,neural network classifier,phonetic class recognizer,speaking rate feature,speaking rate parameter performance,speech,Emotion Recognition,Speaking Rate
Conference
1945-7871
ISBN
Citations 
PageRank 
978-1-4673-1659-0
8
0.57
References 
Authors
8
4
Name
Order
Citations
PageRank
David Philippou-Hubner180.57
Bogdan Vlasenko223512.72
Ronald Bock3372.45
Andreas Wendemuth445141.74