Speech recognition for DARPA Communicator
A. Aaron, Shuyi Chen, P. Cohen, Satya Dharanipragada, Ellen Eide, Martin Franz, J.-M. Leroux, Xiyang Luo, Benoit Maison, Lidia Mangu, Timothy K. Mathes, Miroslav M Novak, Peder A. Olsen, Michael Picheny, Harry Printz, Bhuvana Ramabhadran, A. Sakrajda, George Saon, B. Tydlitat, Karthik Visweswariah · 2002
We report the results of investigations in acoustic modeling, language modeling and decoding techniques, for the DARPA Communicator, a speaker-independent, telephone-based dialog system. By a combination of methods, including enlarging the acoustic model, augmenting the recognizer vocabulary, conditioning the language model upon the dialog state, and applying a post-processing decoding method, we lowered the overall word error rate from 21.9% to 15.0%, a gain of 6.9% absolute and 31.5% relative.