Name
Abstract | ||
|---|---|---|
Recently, automatic emotion recognition from speech has achieved growing interest within the human-machine interaction research community. Most part of emotion recognition methods use context independent frame-level analysis or turn-level analysis. In this article, we introduce context dependent vowel level analysis applied for emotion classification. An average first formant value extracted on vowel level has been used as unidimensional acoustic feature vector. The Neyman-Pearson criterion has been used for classification purpose. Our classifier is able to detect high-arousal emotions with small error rates. Within our research we proved that the smallest emotional unit should be the vowel instead of the word. We find out that using vowel level analysis can be an important issue during developing a robust emotion classifier. Also, our research can be useful for developing robust affective speech recognition methods and high quality emotional speech synthesis systems. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICME.2011.6012003 | ICME |
Keywords | Field | DocType |
emotion recognition method,robust emotion classifier,emotion classification,context dependent vowel level,turn-level analysis,high-arousal emotion,automatic emotion recognition,vowel level analysis,context independent frame-level analysis,vowels formants analysis,high arousal emotion,straightforward detection,vowel level,context dependent,speech recognition,feature vector,error rate,materials,gold,speech synthesis,speech,estimation,accuracy | Arousal,Speech synthesis,Feature vector,Computer science,Emotion classification,Speech recognition,Natural language processing,Vowel,Artificial intelligence,Affect (psychology),Classifier (linguistics),Formant | Conference |
ISSN | Citations | PageRank |
1945-7871 | 13 | 0.65 |
References | Authors | |
8 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bogdan Vlasenko | 1 | 235 | 12.72 |
| David Philippou-Hubner | 2 | 13 | 0.65 |
| Dmytro Prylipko | 3 | 66 | 4.65 |
| Ronald Bock | 4 | 37 | 2.45 |
| Ingo Siegert | 5 | 101 | 13.20 |
| Andreas Wendemuth | 6 | 451 | 41.74 |