We describe feature space and model space discriminative training for a new class of acoustic models called Bayesian sensing hidden Markov models (BS-HMMs). In BS-HMMs, speech dat...
Abstract—We present an algorithm for removing timefrequency components, found by a standard Gabor transform, of a “real-world” sound while causing no audible difference to th...
We consider a finite-state memoryless channel with i.i.d. channel state and the input Markov process supported on a mixing finite-type constraint. We discuss the asymptotic behavio...
The voice activity detectors (VADs) based on statistical models have shown impressive performances especially when fairly precise statistical models are employed. Moreover, the ac...
Abstract. This paper describes the 2007 meeting speech-to-text system for lecture rooms developed at the Interactive Systems Laboratories (ISL), for the multiple distant microphone...