Paper: The Lincoln Large-Vocabulary Stack-Decoder Based HMM CSR

ACL ID H94-1079
Title The Lincoln Large-Vocabulary Stack-Decoder Based HMM CSR
Venue Human Language Technologies
Session Main Conference
Year 1994

The system described here is a large.vocabulary continuous-speech recognition (CSR) system with results obtained using the Wall Street Journal-based database [15]. The recognizer uses a stack decoder-based search strategy[l, 7, 14] with a left-to-rlght stochas- tic language model. This decoder has been shown to function effec- tively on 20K and 64K-word recognition of continuous speech. It operates left-to-right and can produce final textual output while continuing to accept additional input speech. Thus it need not wait for the end of the sentence and can be structured so that it can accept an unbounded length stream of input speech. The recognizer also features recognition-time adaptation to the user's voice. This system showed improvements of 42% for a 5K vocab- nlary and 35% for a 20K ...