Rhetorical-State Hidden Markov Models for extractive speech summarization

We propose an extractive summarization system with a novel non-generative probabilistic framework for speech summarization. One of the most underutilized features in extractive summarization is rhetorical information – semantically cohesive units that are hidden in spoken documents. We propose Rhetorical-State Hidden Markov Models (RSHMMs) to automatically decode this underlying

• Type: Conference
• Year: 2008
• Where: ICASSP
• Authors: Pascale Fung, Ricky Ho Yin Chan, Justin Jian Zhang
• Keywords: Extractive Summarization, ICASSP 2008, Non-generative Probabilistic Framework, Signal Processing, Speech Summarization