A front-end for emotional speech classification based on new sub-band filters
Authors:
- 1 May 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 421-425
Abstract
Emotional state of speaker is among many information included in the speech signal that is ignored in Automatic speech recognition (ASR). An automatic emotion detection system bears the task of extracting appropriate features that could represent the emotional characteristics of the speaker. This study is focused on finding more effective features in frequency domain for speaker emotional state classification. Here, we replace Mel filters with new filter banks, designed according to the data and the importance of emotional components. This approach is based on Kullback-Leibler divergence (KLD) and F-ratio. The new filter banks have led to an improvement in the emotion recognition system performance of about 3.2% on average, in comparison with the baseline system, mel frequency cepstral coefficients (MFCC).Keywords
This publication has 8 references indexed in Scilit:
- Speech emotion classification via a modified Gaussian Mixture Model approach2014
- Use of Line Spectral Frequencies for Emotion Recognition from Speech2010
- Analysis of Emotionally Salient Aspects of Fundamental Frequency for Emotion DetectionIEEE Transactions on Audio, Speech, and Language Processing, 2009
- A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous ExpressionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- The Relevance of Voice Quality Features in Speaker Independent Emotion Recognition2007
- Ensemble methods for spoken emotion recognition in call-centresSpeech Communication, 2007
- Toward detecting emotions in spoken dialogsIEEE Transactions on Speech and Audio Processing, 2005
- Acoustical properties of speech as indicators of depression and suicidal riskIEEE Transactions on Biomedical Engineering, 2000