Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...
Hidden Markov models play a critical role in the modelling and problem solving of important AI tasks such as speech recognition and natural language processing. However, the stude...
Automatic extraction of content description from commercial audio recordings has a number of important applications, from indexing and retrieval through to novel musicological ana...
The BYBLOS continuous speech recognition system is applied to on-line cursive handwriting recognition. By exploiting similarities between on-line cursive handwriting and continuou...
John Makhoul, Thad Starner, Richard M. Schwartz, G...