Performance of SRI's DECIPHER#8482; speech recognition system on DARPA's CSR task

Abstract

SRI has ported its DECIPHER™ speech recognition system from DARPA's ATIS domain to DARPA's CSR domain (read and spontaneous Wall Street Journal speech). This paper describes what needed to be done to port DECIPHER™, and reports experiments performed with the CSR task.The system was evaluated on the speaker-independent (SI) portion of DARPA's February 1992 "Dry-Run" WSJ0 test and achieved 17.1% word error without verbalized punctuation (NVP) and 16.6% error with verbalized punctuation (VP). In addition, we increased the amount of training data and reduced the VP error rate to 12.9%. This SI error rate (with a larger amount of training data) equalled the best 600-training-sentence speaker-dependent error rate reported for the February CSR evaluation. Finally, the system was evaluated on the VP data using microphones unknown to the system instead of the training-set's Sennheiser microphone and the error rate only increased to 26.0%.