Conference Paper

Recognition of stress in speech using wavelet analysis and Teager energy operator.

Conference: INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, September 22-26, 2008
Source: DBLP
  • [Show abstract] [Hide abstract]
    ABSTRACT: The automatic speech emotion recognition has important applications in human-machine communication. Majority of current research in this area is focused on finding optimal feature parameters. In recent studies, several glottal features were examined as potential cues for emotion differentiation. In this study, a new type of feature parameter is proposed, which calculates energy entropy on values within selected Wavelet Packet frequency bands. The modeling and classification tasks are conducted using the classical GMM algorithm. The experiments use two data sets: the Speech Under Simulated Emotion (SUSE) data set annotated with three different emotions (angry, neutral and soft) and Berlin Emotional Speech (BES) database annotated with seven different emotions (angry, bored, disgust, fear, happy, sad and neutral). The average classification accuracy achieved for the SUSE data (74%-76%) is significantly higher than the accuracy achieved for the BES data (51%-54%). In both cases, the accuracy was significantly higher than the respective random guessing levels (33% for SUSE and 14.3% for BES).
    Proceedings of SPIE - The International Society for Optical Engineering 07/2013; DOI:10.1117/12.2030929 · 0.20 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The classification of emotional speech is mostly considered in speech-related research on human-computer interaction (HCI). In this paper, the purpose is to present a novel feature extraction based on multi-resolutions texture image information (MRTII). The MRTII feature set is derived from multi-resolution texture analysis for characterization and classification of different emotions in a speech signal. The motivation is that we have to consider emotions have different intensity values in different frequency bands. In terms of human visual perceptual, the texture property on multi-resolution of emotional speech spectrogram should be a good feature set for emotion classification in speech. Furthermore, the multi-resolution analysis on texture can give a clearer discrimination between each emotion than uniform-resolution analysis on texture. In order to provide high accuracy of emotional discrimination especially in real-life, an acoustic activity detection (AAD) algorithm must be applied into the MRTII-based feature extraction. Considering the presence of many blended emotions in real life, in this paper make use of two corpora of naturally-occurring dialogs recorded in real-life call centers. Compared with the traditional Mel-scale Frequency Cepstral Coefficients (MFCC) and the state-of-the-art features, the MRTII features also can improve the correct classification rates of proposed systems among different language databases. Experimental results show that the proposed MRTII-based feature information inspired by human visual perception of the spectrogram image can provide significant classification for real-life emotional recognition in speech.
    Sensors 01/2015; 15(1):1458-1478. DOI:10.3390/s150101458 · 2.05 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a novel texture image feature for Emotion Sensing in Speech (ESS). This idea is based on the fact that the texture images carry emotion-related information. The feature extraction is derived from time-frequency representation of spectrogram images. First, we transform the spectrogram as a recognizable image. Next, we use a cubic curve to enhance the image contrast. Then, the texture image information (TII) derived from the spectrogram image can be extracted by using Laws' masks to characterize emotional state. In order to evaluate the effectiveness of the proposed emotion recognition in different languages, we use two open emotional databases including the Berlin Emotional Speech Database (EMO-DB) and eNTERFACE corpus and one self-recorded database (KHUSC-EmoDB), to evaluate the performance cross-corpora. The results of the proposed ESS system are presented using support vector machine (SVM) as a classifier. Experimental results show that the proposed TII-based feature extraction inspired by visual perception can provide significant classification for ESS systems. The two-dimensional (2-D) TII feature can provide the discrimination between different emotions in visual expressions except for the conveyance pitch and formant tracks. In addition, the de-noising in 2-D images can be more easily completed than de-noising in 1-D speech.
    Sensors 09/2014; 14(9):16692-16714. DOI:10.3390/s140916692 · 2.05 Impact Factor