Abstract | ||
---|---|---|
We present a 1000-word continuous speech recognition (CSR) system that operates in real time on a personal computer (PC). The system, designed for large vocabulary natural language tasks, makes use of phonetic Hidden Markov models (HMM) and incorporates acoustic, phonetic, and linguistic sources of knowledge to achieve high recognition performance. We describe the various components of this system. We also present our strategy for achieving real time recognition on the PC. Using a 486-based PC with a 29K-based add-on board, the recognizer has been timed at 1.1 times real time. |
Year | DOI | Venue |
---|---|---|
1990 | 10.3115/116580.116610 | HLT |
Keywords | Field | DocType |
large vocabulary natural language,phonetic hidden markov model,times real time,real-time implementation,486-based pc,linguistic source,add-on board,1000-word continuous speech recognition,real time recognition,real time,dragon continuous speech recognition,high recognition performance | Computer science,Personal computer,Speech recognition,Natural language,Natural language processing,Continuous speech recognition system,Artificial intelligence,Hidden Markov model,Vocabulary | Conference |
Citations | PageRank | References |
7 | 9.86 | 2 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paul Bamberg | 1 | 40 | 25.80 |
Yen-Lu Chow | 2 | 148 | 70.09 |
Laurence Gillick | 3 | 35 | 28.38 |
Robert Roth | 4 | 46 | 27.12 |
Dean Sturtevant | 5 | 91 | 37.38 |