Speech is one of the most important signals that can be used to detect human emotions. Speech is modulated by different emotions by varying frequency- and energy-related acoustic parameters such as pitch, energy, and formants. In this paper, we describe research on analyzing inter- and intra-subband energy variations to differentiate five emotions. The emotions considered are anger, fear, dislike, sadness, and neutral. We employ a Two-Layered Cascaded Subband (TLCS) filter to study the energy variations for extraction of acoustic features. Experiments were conducted on the Berlin Emotional Data Corpus (BEDC). We achieve average accuracy of 76.4% and 69.3% for speaker-dependent and -independent emotion classifications, respectively.
Bibliographic reference. Amarakeerthi, Senaka / Nwe, Tin Lay / Silva, Liyanage C. De / Cohen, Michael (2011): "Emotion classification using inter- and intra-subband energy variation", In INTERSPEECH-2011, 1569-1572.