2005 Special Issue: Emotion recognition in human-computer interaction
Neural Networks - Special issue: Emotion and brain
Primitives-based evaluation and estimation of emotions in speech
Speech Communication
Advances in Human-Computer Interaction - Special issue on emotion-aware natural interaction
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Automatic speech emotion recognition using modulation spectral features
Speech Communication
IEEE Transactions on Affective Computing
Recognizing affect from speech prosody using hierarchical graphical models
Speech Communication
Vowels formants analysis allows straightforward detection of high arousal emotions
ICME '11 Proceedings of the 2011 IEEE International Conference on Multimedia and Expo
Emotional Audio-Visual Speech Synthesis Based on PAD
IEEE Transactions on Audio, Speech, and Language Processing
A dynamic tonal perception model for optimal pitch stylization
Computer Speech and Language
| Hi-index | 0.00 |
As research on the extraction of acoustic properties of speech for emotion recognition progresses, the need of investigating methods of feature extraction taking into account the necessities of real time processing systems becomes more important. Past works have shown the importance of syllables for the transmission of emotions, while classical research methods adopted in prosody show that it is important to concentrate on specific areas of the speech signal to study intonation phenomena. Technological approaches, however, are often designed to use the whole speech signal without taking into account the qualitative variability of the spectral content. Given this contrast with the theoretical basis around which prosodic research is pursued, we present here a feature extraction method built on the basis of a phonetic interpretation of the concept of syllable. In particular, we concentrate on the spectral content of syllabic nuclei, thus reducing the amount of information to be processed. Moreover, we introduce feature weighting based on syllabic prominence, thus not considering all the units of analysis as being equally important. The method is evaluated on a continuous, three-dimensional model of emotions built on the classical axes of Valence, Activation and Dominance and is shown to be competitive with state-of-the-art performance. The potential impact of this approach on the design of affective computing systems is also analysed.