Abstract
A complete emotional expression typically contains a complex temporal course in a natural conversation. Related research on utterance-level and segment-level processing lacks understanding of the underlying structure of emotional speech. In this study, a hierarchical affective structure of an emotional utterance characterized by the probabilistic context free grammars (PCFGs) is proposed for emotion modeling. SVM-based emotion profiles are obtained and employed to segment the utterance into emotionally consistent segments. Vector quantization is applied to convert the emotion profile of each segment into codewords. A binary tree in which each node represents a codeword is constructed to characterize the affective structure of the utterance modeled by PCFG. Given an input utterance, the output emotion is determined according to the PCFG-based emotion model with the highest likelihood of the speech segments along with the score of the affective structure. For evaluation, the EMO-DB database and its expansion in utterance length were conducted. Experimental results show that the proposed method achieved emotion recognition accuracy of 87.22% for long utterances and outperformed the SVM-based method.
| Original language | English |
|---|---|
| Title of host publication | 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 5286-5290 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781467369978 |
| DOIs | |
| Publication status | Published - 2015 Aug 4 |
| Event | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 2014 Apr 19 → 2014 Apr 24 |
Publication series
| Name | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
|---|---|
| Volume | 2015-August |
| ISSN (Print) | 1520-6149 |
Other
| Other | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 |
|---|---|
| Country | Australia |
| City | Brisbane |
| Period | 14-04-19 → 14-04-24 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Signal Processing
- Electrical and Electronic Engineering
Cite this
}
Affective structure modeling of speech using probabilistic context free grammar for emotion recognition. / Huang, Kun Yi; Lin, Jia Kuan; Chiu, Yu Hsien; Wu, Chung-Hsien.
2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 5286-5290 7178980 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2015-August).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Affective structure modeling of speech using probabilistic context free grammar for emotion recognition
AU - Huang, Kun Yi
AU - Lin, Jia Kuan
AU - Chiu, Yu Hsien
AU - Wu, Chung-Hsien
PY - 2015/8/4
Y1 - 2015/8/4
N2 - A complete emotional expression typically contains a complex temporal course in a natural conversation. Related research on utterance-level and segment-level processing lacks understanding of the underlying structure of emotional speech. In this study, a hierarchical affective structure of an emotional utterance characterized by the probabilistic context free grammars (PCFGs) is proposed for emotion modeling. SVM-based emotion profiles are obtained and employed to segment the utterance into emotionally consistent segments. Vector quantization is applied to convert the emotion profile of each segment into codewords. A binary tree in which each node represents a codeword is constructed to characterize the affective structure of the utterance modeled by PCFG. Given an input utterance, the output emotion is determined according to the PCFG-based emotion model with the highest likelihood of the speech segments along with the score of the affective structure. For evaluation, the EMO-DB database and its expansion in utterance length were conducted. Experimental results show that the proposed method achieved emotion recognition accuracy of 87.22% for long utterances and outperformed the SVM-based method.
AB - A complete emotional expression typically contains a complex temporal course in a natural conversation. Related research on utterance-level and segment-level processing lacks understanding of the underlying structure of emotional speech. In this study, a hierarchical affective structure of an emotional utterance characterized by the probabilistic context free grammars (PCFGs) is proposed for emotion modeling. SVM-based emotion profiles are obtained and employed to segment the utterance into emotionally consistent segments. Vector quantization is applied to convert the emotion profile of each segment into codewords. A binary tree in which each node represents a codeword is constructed to characterize the affective structure of the utterance modeled by PCFG. Given an input utterance, the output emotion is determined according to the PCFG-based emotion model with the highest likelihood of the speech segments along with the score of the affective structure. For evaluation, the EMO-DB database and its expansion in utterance length were conducted. Experimental results show that the proposed method achieved emotion recognition accuracy of 87.22% for long utterances and outperformed the SVM-based method.
UR - http://www.scopus.com/inward/record.url?scp=84946036727&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84946036727&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2015.7178980
DO - 10.1109/ICASSP.2015.7178980
M3 - Conference contribution
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5286
EP - 5290
BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
ER -