Name
Abstract | ||
|---|---|---|
The importance of automatically recognizing emotions from human speech has grown with the increasing role of spoken language interfaces in human-computer interaction applications. This paper explores the detection of domain-specific emotions using language and discourse information in conjunction with acoustic correlates of emotion in speech signals. The specific focus is on a case study of detecting negative and non-negative emotions using spoken language data obtained from a call center application. Most previous studies in emotion recognition have used only the acoustic information contained in speech. In this paper, a combination of three sources of information-acoustic, lexical, and discourse-is used for emotion recognition. To capture emotion information at the language level, an information-theoretic notion of emotional salience is introduced. Optimization of the acoustic correlates of emotion with respect to classification error was accomplished by investigating different feature sets obtained from feature selection, followed by principal component analysis. Experimental results on our call center data show that the best results are obtained when acoustic and language information are combined. Results show that combining all the information, rather than using only acoustic information, improves emotion classification by 40.7% for males and 36.4% for females (linear discriminant classifier used for acoustic information). |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/TSA.2004.838534 | IEEE Transactions on Speech and Audio Processing |
Keywords | Field | DocType |
spoken language interface,optimisation,spoken dialog,speech processing,automatically recognizing emotion,error classification,human computer interaction,call centres,human-computer interaction application,information fusion,human speech,dialog systems,call center application,acoustic correlates,spoken language processing.,acoustic correlation,emotion recognition,domain-specific emotion detection,emotional salience,index terms—acoustic correlates,information-theoretic notion,emotion in speech signal,spoken language processing,feature selection,principal component analysis,indexing terms,automatic speech recognition,signal analysis,psychology,natural languages | Speech processing,Feature selection,Computer science,Emotion classification,Speech recognition,Feature extraction,Natural language,Artificial intelligence,Natural language processing,Linear discriminant analysis,Salience (language),Spoken language | Journal |
Volume | Issue | ISSN |
13 | 2 | 1063-6676 |
Citations | PageRank | References |
291 | 14.65 | 12 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chul Min Lee | 1 | 849 | 53.76 |
| Narayanan Shrikanth | 2 | 5558 | 439.23 |