Integrating Prosodic and Lexical Cues for Automatic Topic Segmentation

Abstract

We present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topically coherent units. We propose two methods for combining lexical and prosodic information using hidden Markov models and decision trees. Lexical information is obtained from a speech recognizer, and prosodic features are extracted automatically from speech waveforms. We evaluate our approach on the Broadcast News corpus, using the DARPA-TDT evaluation metrics. Results show that the prosodic model alone is competitive with word-based segmentation methods. Furthermore, we achieve a significant reduction in error by combining the prosodic and word-based knowledge sources.

27 pages, 8 figures

References in corpus (2)

• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• Prosody-Based Automatic Segmentation of Speech into Sentences and Topics

Cited by in corpus (5)

• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• Prosody-Based Automatic Segmentation of Speech into Sentences and Topics
• Improving automated segmentation of radio shows with audio embeddings
• Towards Modelling Coherence in Spoken Discourse
• Attention-based Neural Text Segmentation