Speech recognition for DARPA Communicator
2002Vol. 1, pp. 489–492
A. Aaron, S. Chen, Paul S. Cohen, S. Dharanipragada, Ellen Eide, Martin Franz, J.-M. Leroux, Xiyang Luo, B. Maison, Lidia Mangu, Timothy K. Mathes, Miroslav Novák, Peder A. Olsen, Michael Picheny, Harry Printz, Bhuvana Ramabhadran, A. Sakrajda, George Saon, B. Tydlitat, Karthik Visweswariah, Dong-Suk Yuk
Abstract
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.
Related Papers
- → Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models(2021)29 cited
- → Capitalization Normalization for Language Modeling with an Accurate and Efficient Hierarchical RNN Model(2022)7 cited
- → Speech recognition experiments using multi-span statistical language models(1999)6 cited
- → Deep Learning Based Language Modeling for Domain-Specific Speech Recognition(2017)1 cited
- → Large Scale Language Modeling in Automatic Speech Recognition(2012)37 cited