Modeling Coarticulation in EMG-based Continuous Speech Recognition

This paper discusses the use of surface electromyography for automatic speech recognition. Electromyographic signals captured at the facial muscles record the activity of the human articulatory apparatus and thus allow to trace back a speech signal even if it is spoken silently. Since speech is captured before it gets airborne, the resulting signal is not masked by ambient noise. The resulting Silent Speech Interface has the potential to overcome major limitations of conventional speech-driven interfaces: it is not prone to any environmental noise, allows to silently transmit confidential information, and does not disturb bystanders. We describe our new approach of phonetic feature bundling for modeling coarticulation in EMG-based speech recognition and report results on the EMG-PIT corpus, a multiple speaker large vocabulary database of silent and audible EMG speech recordings, which we recently collected. Our results on speaker-dependent and speaker-independent setups show that modeling the interdependence of phonetic features reduces the word error rate of the baseline system by over 33% relative. Our final system achieves 10% word error rate for the best-recognized speaker on a 101-word vocabulary task, bringing EMG-based speech recognition within a useful range for the application of silent speech interfaces.