Session-independent EMG-based Speech Recognition

@inproceedings{Wand2011SessionindependentES,
  title={Session-independent EMG-based Speech Recognition},
  author={Michael Wand and Tanja Schultz},
  booktitle={BIOSIGNALS},
  year={2011}
}
This paper reports on our recent research in speech recognition by surface electromyography (EMG), which is the technology of recording the electric activation potentials of the human articulatory muscles by surface electrodes in order to recognize speech. This method can be used to create Silent Speech Interfaces, since the EMG signal is available even when no audible signal is transmitted or captured. Several past studies have shown that EMG signals may vary greatly between different… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Our best session-independent recognition system, trained on 280 utterances of 7 different sessions, achieves an average 21.93% Word Error Rate (WER) on a testing vocabulary of 108 words.
  • The average word error rate of our largest SI systems with 280 training sentences is 21.94%, compared to a WER of 11.28% for the speaker-dependent system of the same size.

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 36 CITATIONS

Compensation of recording position shifts for a myoelectric Silent Speech Recognizer

  • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Towards real-life application of EMG-based speech recognition by using unsupervised adaptation

  • INTERSPEECH
  • 2014
VIEW 8 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Statistical conversion of silent articulation into audible speech using full-covariance HMM

  • Computer Speech & Language
  • 2016
VIEW 2 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Tackling Speaking Mode Varieties in EMG-Based Speech Recognition

  • IEEE Transactions on Biomedical Engineering
  • 2014
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

The EMG-UKA corpus for electromyographic speech processing

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

Silent speech interfaces

  • Speech Communication
  • 2010
VIEW 1 EXCERPT

Continuous Electromyographic Speech Recognition with a Multi-Stream Decoding Architecture

  • 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
  • 2007
VIEW 3 EXCERPTS

ditory Speech Recognition Based on EMG / EPG Signals

C. Jorgensen, D. Lee, S. Agabon
  • Proceedings of International Joint Conference on Neural Networks ( IJCNN )
  • 2003
VIEW 1 EXCERPT