|IS&T/SPIE's Electronic Imaging 2004
|San Jose, CA, USA
|Hyoung-Gook Kim, Thomas Sikora
|Automatic segmentation of speakers in broadcast audio material
|In this paper, dimension-reduced, decorrelated spectral features for general sound recognition are applied to segment conversational speech of both broadcast news audio and panel discussion television programs. Without a priori information about number of speakers, the audio stream is segmented by a hybrid metric-based and model-based segmentation algorithm. For the measure of the performance we compare the segmentation results of the hybrid method versus metric-based segmentation with both the MPEG-7 standardized features and Mel-scale Frequency Cepstrum Coefficients (MFCC). Results show that the MFCC features yield better performance compared to MPEG-7 features. The hybrid approach significantly outperforms direct metric based segmentation.
|MPEG-7, Metric-Based and Model-Based Segmentation, Mel-scale Frequency Cepstrum Coefficients (MFCC)