Paper: Making Sense of Sound: Unsupervised Topic Segmentation over Acoustic Input

ACL ID P07-1064
Title Making Sense of Sound: Unsupervised Topic Segmentation over Acoustic Input
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2007
Authors

We address the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to ex- isting algorithms for topic segmentation of speech, our approach does not require in- put transcripts. Our method predicts topic changes by analyzing the distribution of re- occurring acoustic patterns in the speech sig- nal corresponding to a single speaker. The algorithm robustly handles noise inherent in acoustic matching by intelligently aggregat- ing information about the similarity profile from multiple local comparisons. Our ex- periments show that audio-based segmen- tation compares favorably with transcript- based segmentation computed over noisy transcripts. These results demonstrate the desirability of our method for applications where a speech recogn...