The detection of prosodic characteristics is an important aspect of both speech synthesis and speech recognition. Correct placement of pitch accents aids in more natural sounding ...
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...
Conditional random fields for sequence labeling offer advantages over both generative models like HMMs and classifiers applied at each sequence position. Among sequence labeling...
We describe a probabilistic approach to content selection for meeting summarization. We use skipchain Conditional Random Fields (CRF) to model non-local pragmatic dependencies bet...
Conditional random field (CRF) is a popular graphical model for sequence labeling. The flexibility of CRF poses significant computational challenges for training. Using existing o...