Paper: Towards Using EEG to Improve ASR Accuracy

ACL ID N12-1042
Title Towards Using EEG to Improve ASR Accuracy
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2012

We report on a pilot experiment to improve the per- formance of an automatic speech recognizer (ASR) by using a single-channel EEG signal to classify the speaker?s mental state as reading easy or hard text. We use a previously published method (Mostow et al., 2011) to train the EEG classifier. We use its prob- abilistic output to control weighted interpolation of separate language models for easy and difficult read- ing. The EEG-adapted ASR achieves higher accu- racy than two baselines. We analyze how its perfor- mance depends on EEG classification accuracy. This pilot result is a step towards improving ASR more generally by using EEG to distinguish mental states.