Making Sense of Sound: Unsupervised Topic Segmentation over Acoustic Input

We address the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to existing algorithms for topic segmentation of speech, our approach does not require input transcripts. Our method predicts topic changes by analyzing the distribution of reoccurring acoustic patterns in the speech signal corresponding to a single speaker. The algorithm robustly handles noise inherent in acoustic matching by intelligently aggregating information about the similarity profile from multiple local comparisons. Our experiments show that audio-based segmentation compares favorably with transcriptbased segmentation computed over noisy transcripts. These results demonstrate the desirability of our method for applications where a speech recognizer is not available, or its output has a high word error rate.

• Type: Conference
• Year: 2007
• Where: ACL
• Authors: Igor Malioutov, Alex Park, Regina Barzilay, James R. Glass
• Keywords: ACL 2007, Computational Linguistics, Method Predicts Topic, Topic Segmentation, Unsupervised Topic Segmentation