Paper Info
Title
Angry emotion detection from real-life conversational speech by leveraging content structure
Abstract
This study proposes an effective angry speech detection approach by leveraging content structure within the input speech. A classifier based on an “emotional” language model score is formulated and combined with acoustic feature based classifiers including TEO-based feature and conventional Mel frequency cepstral coefficients (MFCC). The proposed detection algorithm is evaluated on real-life conversational speech which was recorded between customers and call center operators over a telephone network. Analysis on the conversational speech corpus presents a distinctive property between neutral and angry speech in word distribution and frequently occurring words. An improvement of up to 6.23% in Equal Error Rate (EER) is obtained by combining the TEO-based and MFCC features, and emotional language model score based classifiers.
Year
DOI
Venue
2010
10.1109/ICASSP.2010.5495021
ICASSP
Keywords
Field
DocType
leveraging content structure,conventional mel frequency cepstral coefficients,natural languages,content structure,angry speech detection,equal error rate,emotion recognition,angry emotion detection,teo-based feature,real-life conversational speech,telephone network,speech,emotional language model,classifier combination,data models,speech detection,mel frequency cepstral coefficient,network analysis,speech processing,feature extraction,speech recognition,stress,robustness,telephony,language model
Speech corpus,Speech enhancement,Speech processing,Mel-frequency cepstrum,Computer science,Voice activity detection,Word error rate,Speech recognition,Natural language,Natural language processing,Artificial intelligence,Language model
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4244-4296-6
978-1-4244-4296-6
5
PageRank 
References 
Authors
0.54
4
2
Name
Order
Citations
PageRank
Wooil Kim112016.95
John H. L. Hansen23215365.75