Surface Electromyography Based Speech Recognition System and Development Toolkit by Daniel Chang Thesis

This thesis describes the implementation of an automatic speech recognition system based on surface electromyography signals. Data collection was done using a bipolar electrode configuration with a sampling rate of 5.77 kHz. Four feature sets, the shorttime Fourier transform (STFT), the dual-tree complex wavelet transform (DTCWT), a non-causal time-domain based (E4-NC), and a causal version of E4-NC (E4-C) were implemented. Classification was performed using a hidden Markov model (HMM). The system implemented was able to achieve an accuracy rate of 74.24% with E4-NC and 61.25% with E4-C. These results are comparable to previously reported results for offline, single session, isolated word recognition. Additional testing was performed on five subjects using E4-C and yielded accuracy rates ranging from 51.8% to 81.88% with an average accuracy rate of 64.9% during offline, single session, isolated word recognition. The E4-C was chosen since it offered the best performance among the causal feature sets and non-causal feature sets cannot be used with real-time online classification. Online classification capabilities were implemented and simulations using the confidence interval (CI) and minimum noise likelihood (MNL) decision rubrics yielded accuracy rates of 77.5% and 72.5%, respectively, during online, single session, isolated word recognition.