We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
We propose a novel utterance comparison model based on probability theory and factor analysis that computes the likelihood of two speech utterances originating from the same speak...
We present a statistical model for canonicalizing named entity mentions into a table whose rows represent entities and whose columns are attributes (or parts of attributes). The m...
High-dimensional data poses a severe challenge for data mining. Feature selection is a frequently used technique in preprocessing high-dimensional data for successful data mining....
Abstract. Some recent works have addressed the object recognition problem by representing objects as the composition of independent image parts, where each part is modeled with “...