Formant position based weighted spectral features for emotion recognition

Name: Formant position based weighted spectral features for emotion recognition
Author: Bozkurt, E., Erzin, E., Eroğlu Erdem, Ç., Erdem, Tanju

İsim	Formant position based weighted spectral features for emotion recognition
Yazar	Bozkurt, E., Erzin, E., Eroğlu Erdem, Ç., Erdem, Tanju
Basım Tarihi:	2011
Basım Yeri	- Elsevier
Konu	Emotion recognition, Emotional speech classification, Spectral features
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	0092-2102
Kayıt Numarası	cfeaa677-4cb5-45dc-9863-358d454b45c2
Lokasyon	Computer Science
Tarih	2011
Notlar	TÜBİTAK
Örnek Metin	In this paper, we propose novel spectrally weighted mel-frequency cepstral coefficient (WMFCC) features for emotion recognition from speech. The idea is based on the fact that formant locations carry emotion-related information, and therefore critical spectral bands around formant locations can be emphasized during the calculation of MFCC features. The spectral weighting is derived from the normalized inverse harmonic mean function of the line spectral frequency (LSF) features, which are known to be localized around formant frequencies. The above approach can be considered as an early data fusion of spectral content and formant location information. We also investigate methods for late decision fusion of unimodal classifiers. We evaluate the proposed WMFCC features together with the standard spectral and prosody features using HMM based classifiers on the spontaneous FAU Aibo emotional speech corpus. The results show that unimodal classifiers with the WMFCC features perform significantly better than the classifiers with standard spectral features. Late decision fusion of classifiers provide further significant performance improvements.
DOI	10.1016/j.specom.2011.04.003
Cilt	53

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Formant position based weighted spectral features for emotion recognition

Yazar Bozkurt, E., Erzin, E., Eroğlu Erdem, Ç., Erdem, Tanju

Basım Tarihi 2011

Basım Yeri - Elsevier

Konu Emotion recognition, Emotional speech classification, Spectral features

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 0092-2102

Kayıt Numarası cfeaa677-4cb5-45dc-9863-358d454b45c2

Lokasyon Computer Science

Tarih 2011

Notlar TÜBİTAK

Örnek Metin In this paper, we propose novel spectrally weighted mel-frequency cepstral coefficient (WMFCC) features for emotion recognition from speech. The idea is based on the fact that formant locations carry emotion-related information, and therefore critical spectral bands around formant locations can be emphasized during the calculation of MFCC features. The spectral weighting is derived from the normalized inverse harmonic mean function of the line spectral frequency (LSF) features, which are known to be localized around formant frequencies. The above approach can be considered as an early data fusion of spectral content and formant location information. We also investigate methods for late decision fusion of unimodal classifiers. We evaluate the proposed WMFCC features together with the standard spectral and prosody features using HMM based classifiers on the spontaneous FAU Aibo emotional speech corpus. The results show that unimodal classifiers with the WMFCC features perform significantly better than the classifiers with standard spectral features. Late decision fusion of classifiers provide further significant performance improvements.

DOI 10.1016/j.specom.2011.04.003

Cilt 53