Techniques to achieve an accurate real-time large-vocabulary speech recognition system

Hy Murveit, Peter Monaco, Vassilios Digalakis, John Butzberger
1994 Proceedings of the workshop on Human Language Technology - HLT '94   unpublished
In addressing the problem of achieving high-accuracy real-time speech recognition systems, we focus on recognizing speech from ARPA's 20,000-word Wall Street Journal (WSJ) task, using MODELING TRADE-OFFS The speed/accuracy trade-off of our speech recognition systems can be adjusted in several ways. The standard approaches are to adjust the beam width of the Viterbi search and to change the
doi:10.3115/1075812.1075903 fatcat:3rbkqinkyjgy3lzef5v3gc3kp4