Articulatory features for large vocabulary speech recognition

Content Provider	Microsoft Research
Author	Mitra, Vikramjit Wang, Wen Stolcke, Andreas Nam, Hosung Richey, Colleen Yuan, Jiahong Liberman, Mark
Copyright Year	2013
Abstract	Studies have demonstrated that articulatory information can model speech variability effectively and can potentially help to improve speech recognition performance. Most of the studies involving articulatory information have focused on effectively estimating them from speech, and few studies have actually used such features for speech recognition. Speech recognition studies using articulatory information have been mostly confined to digit or medium vocabulary speech recognition, and efforts to incorporate them into large vocabulary systems have been limited. We present a neural network model to estimate articulatory trajectories from speech signals where the model was trained using synthetic speechsignals generated by Haskins Laboratories task-dynamic model of speech production. The trained model was applied to natural speech, and the estimated articulatory trajectories obtained from the models were used in conjunction with standard cepstral features to train acoustic models for large-vocabulary recognition systems. Two different large-vocabulary English datasets were used in the experiments reported here. Results indicate that employing articulatory information improves speech recognition performance not only under clean conditions but also under noisy background conditions. Perceptually motivated robust features were also explored in this study and the best performance was obtained when systems based on articulatory, standard cepstral and perceptually motivated feature were all combined.
Starting Page	7145
Ending Page	7149
Page Count	5
Language	English
Publisher	Proc
Publisher Date	2013-05-01
Publisher Place	Vancouver
Access Restriction	Open
Rights Holder	Microsoft Corporation
Subject Keyword	Human-computer interaction
Content Type	Text
Resource Type	Proceeding