We present Promodes, an algorithm for unsupervised word decomposition, which is based on a probabilistic generative model. The model considers segment boundaries as hidden variable...
Desktop Grids have emerged as an important methodology to harness the idle cycles of millions of participant desktop PCs over the Internet. However, to effectively utilize the res...
Recently, many works have been proposed in the area of cognitive radio to efficiently utilize the spectrum for data communication. However, little effort has been made in content...
We present a novel language identification technique using our recently developed deep-structured conditional random fields (CRFs). The deep-structured CRF is a multi-layer CRF mo...
Many of the existing machine-learning approaches to speech summarization cast important sentence selection as a two-class classification problem and have shown empirical success f...