Progress in recognizing conversational telephone speech

This paper describes improvements made to Dragon´s speech recognition system which have improved performance on Switchboard recognition by roughly 10 percentage points in the past year. These features include the use of rapid speaker adaptation, a move from a 20 to a 10 msec frame rate for recognition, expansion of the acoustic training set and lexicon, and the introduction of interpolated language models. Preliminary results applying this Switchboard-trained system to conversations drawn from the English Call-Home corpus are also quite strong, suggesting that this technology ports well to novel tasks. Finally, the paper includes a report on several research projects which show promise of further reducing the error rate