论文信息 - Emotion recognition from the human voice

Emotion recognition from the human voice

Speech is the most important communication tool between humans and is thousands of years old. As known human voice is a biometric feature like fingerprint and carries the emotional state of the speaker. Therefore, speech data acquired from live talks may have more realistic emotional features than textual data. In this work, we will try to determine whether a speaker independent speech is angry, neutral, happy or sad.

Banu Diri | Cevahir Parlak

[1] Björn W. Schuller,et al. Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge , 2011, Speech Commun..

[2] Joseph Polifroni,et al. Can prosody inform sentiment analysis? Experiments on short spoken reviews , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3] Björn W. Schuller,et al. Acoustic emotion recognition: A benchmark comparison of performances , 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

[4] Yixiong Pan,et al. SPEECH EMOTION RECOGNITION USING SUPPORT VECTOR MACHINE , 2010 .

[5] S. Ramakrishnan. Recognition of Emotion from Speech: A Review , 2012 .

[6] Ruili Wang,et al. Real-time spoken affect classification and its application in call-centres , 2005, Third International Conference on Information Technology and Applications (ICITA'05).

[8] Ronald W. Schafer,et al. Introduction to Digital Speech Processing , 2007, Found. Trends Signal Process..

[9] Tiago H. Falk,et al. Automatic speech emotion recognition using modulation spectral features , 2011, Speech Commun..

[10] A. Tanju Erdem,et al. INTERSPEECH 2009 Duygu Tanma Yarmas Deerlendirmesi INTERSPEECH 2009 Emotion Recognition Challenge Evaluation , 2010 .