8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

METRIC-SEQDAC: A Hybrid Approach for Audio Segmentation

Hsin-min Wang, Shih-sian Cheng

Academia Sinica, Taiwan

This paper presents a hybrid approach for audio segmentation, in which the metric-based segmentation with long sliding windows is applied first to segment an audio stream into shorter sub-segments, and then the divide-and-conquer segmentation is applied to a fixed-length window that slides from the beginning to the end of each sub-segment to sequentially detect the remaining acoustic changes. The experimental results on five one-hour broadcast news shows show that our approach outperforms the existing metric-based and model-selection-based approaches.

Full Paper

Bibliographic reference.  Wang, Hsin-min / Cheng, Shih-sian (2004): "METRIC-SEQDAC: a hybrid approach for audio segmentation", In INTERSPEECH-2004, 1617-1620.