We present a semi-supervised source separation methodology to denoise speech by modeling speech as one source and noise as the other source. We model speech using the recently pro...
Abstract. Bag-of-words model (BOW) is inspired by the text classification problem, where a document is represented by an unsorted set of contained words. Analogously, in the objec...
Mehdi Mirza-Mohammadi, Sergio Escalera, Petia Rade...
Abstract. In recent years, there has been a great deal of work in modeling audio using non-negative matrix factorization and its probabilistic counterparts as they yield rich model...
Expert human input can contribute in various ways to facilitate automatic annotation of natural language text. For example, a part-of-speech tagger can be trained on labeled input...
Marc Carmen, Paul Felt, Robbie Haertel, Deryle Lon...
Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We...