Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectr...
—The paper describes the process of designing a task-oriented continuous speech recognition system for Polish, based on CMU Sphinx4, to be used in the voice interface of a comput...
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...
The use of HMM (Hidden Markov Models) for speech recognition has been successful for various applications in the past decades. However, the use of continuous HMM (CHMM) for melody...
We propose a novelapproach to automaticallygrowing and pruning Hierarchical Mixtures of Experts. The constructive algorithm proposed here enables large hierarchies consisting of s...