View Seminar Video Abstract In this talk, I will first discuss a new unsupervised training algorithm for hidden Markov models that is discriminative, convex, and avoids the use of EM. The idea is to formulate[…]
Research Groups Articulatory Feature-based Speech Recognition Open Source Toolkit for Statistical Machine Translation WS06 Post Workshop Research
Abstract Sensing and decoding human motor activity into a symbolic representation yields information about the state of mind of individuals and their future actions and interactions within their environment. Automatic speech recognition by machines, the[…]
View Seminar Video Abstract Discourse models capture relations across different sentences in a document. These models are crucial in applications where it is important to generate coherent text. Traditionally, rule-based approaches have been predominant in[…]