Combining Acoustic Features for Improved Emotion Recognition in Mandarin Speech.
Tsang-Long PaoYu-Te ChenJun-Heng YehWen-Yuan LiaoPublished in: ACII (2005)
Keyphrases
- emotion recognition
- speaker verification
- acoustic features
- audio visual
- speaker recognition
- emotional speech
- human computer interaction
- audio features
- emotion classification
- facial expressions
- information fusion
- speech signal
- automatic speech recognition
- sentiment analysis
- emotional state
- facial images
- mel frequency cepstral coefficients
- speech recognition
- multi modal
- machine learning
- broadcast news
- visual features
- information retrieval systems
- feature space