We propose an extractive summarization system with a novel non-generative probabilistic framework for speech summarization. One of the most underutilized features in extractive su...
Pascale Fung, Ricky Ho Yin Chan, Justin Jian Zhang
Speech can be represented as a time/frequency distribution of energy using a multi-band filter bank. A Markov random field model, which takes into account the possible time asynch...
We present a maximally streamlined approach to learning HMM-based acoustic models for automatic speech recognition. In our approach, an initial monophone HMM is iteratively refin...