Abstract
We describe the development of the ICSI-SRI speech recognition system for the National Institute of Standards and Technology (NIST) Spring 2006 Meeting Rich Transcription (RT-06S) evaluation, highlighting improvements made since last year, including improvements to the delay-and-sum algorithm, the nearfield segmenter, language models, posterior-based features, HMM adaptation methods, and adapting to a small amount of new lecture data. Results are reported on RT-05S and RT-06S meeting data. Compared to the RT-05S conference system, we achieved an overall improvement of 4pct. relative in the MDM and SDM conditions, and 11pct. relative in the IHM condition. On lecture data, we achieved an overall improvement of 8pct. relative in the SDM condition, 12pct. on MDM, 14pct. on ADM, and 15pct. on IHM.
Share this
