::--Emotion Recognition from speech--::

Summary::

This projects aims to conduct research on emotion recognition from speech of Bangla native speaker. The task can is divided into two phase. First, prepare a database of emotional utterances in Bangla. Then conduct research on the recognition of the emotion from the utterances. In the preliminary stage we are targeting to recognize four emotional states: unemotional (normal), anger, happiness and sadness.

Details::

Recognition of emotions in speech is a complex task that is furthermore complicated by the fact that there is no unambiguous answer to what the “correct” emotion is for a given speech sample. Robust recognition of emotion expressed in speech requires a thorough understanding of the lexical aspects of speech. Automated recognizing emotion without referring any language or linguistic information remains an unclosed problem.

The entire task is divided into two sub tasks where the first one is to collect emotional utterances. As we are targeting to recognize emotion from Bangla speakers, so we have to prepare a database of emotional utterances in Bangla. In our research we are considering four emotional states: unemotional (normal), anger, happiness and sadness. The second task consists of feature extraction and classification.

Team::

• Md. Abul Hasnat [email] [website]
• Mohammed Ehsan Hoque [website]
• Professor Mumit Khan
  

Status::

• Training data of emotional utterances have been prepared.

Timeline:: Not Defined.