Information retrieval methods are frequently used for indexing and retrieving spoken documents, and more recently have been proposed for voice-search amongst a pre-defined set of ...
Geoffrey Zweig, Patrick Nguyen, Jasha Droppo, Alex...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
In this paper, we propose a structure and components of a conversational television set(TV) to which we can ask anything on the broadcasted contents and receive the interesting in...
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
In this paper, we propose a robust compensation strategy to deal effectively with extraneous acoustic variations for spontaneous speech recognition. This strategy extends speaker a...