Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

Monophthong Recognition Optimizing Muscle Mixing Based on Facial Surface EMG Signals

안면근육 표면근전도 신호기반 근육 조합 최적화를 통한 단모음인식

  • Received : 2015.11.05
  • Accepted : 2016.03.07
  • Published : 2016.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose Korean monophthong recognition method optimizing muscle mixing based on facial surface EMG signals. We observed that EMG signal patterns and muscle activity may vary according to Korean monophthong pronunciation. We use RMS, VAR, MMAV1, MMAV2 which were shown high recognition accuracy in previous study and Cepstral Coefficients as feature extraction algorithm. And we classify Korean monophthong by QDA(Quadratic Discriminant Analysis) and HMM(Hidden Markov Model). Muscle mixing optimized using input data in training phase, optimized result is applied in recognition phase. Then New data are input, finally Korean monophthong are recognized. Experimental results show that the average recognition accuracy is 85.7% in QDA, 75.1% in HMM.

본 논문에서는 안면근육 표면근전도를 기반으로 근육 조합 최적화를 통한 한국어 단모음 인식 방법을 제안한다. 표면근전도 신호는 한국어 단모음 발음에 따라 서로 다른 패턴과 근육 활성도를 보였다. 이전 연구에서 높은 인식 정확도를 보였던 RMS, VAR, MMAV1, MMAV2와 Cepstral Coefficients를 특징 추출 알고리즘으로 사용하였으며, QDA(Quadratic Discriminant Analysis)와 HMM(Hidden Markov Model)으로 한국어 단모음을 분류하였다. 트레이닝 단계에서 입력 받은 데이터로 근육조합을 최적화하고, 최적화 결과를 인식단계에 적용한다. 이때, 새로운 근전도 신호를 입력받고 한국어 단모음을 최종 인식한다. 실험결과 제안한 방법의 인식 정확도가 QDA에서 평균 85.7%, HMM에서 평균 75.1%를 보였다.

Keywords

References

  1. Apple Siri, http://www.apple.com/ios/siri/
  2. Google Voice Actions, https://developers.google.com/voice-actions/
  3. S. Kumar, D. K. Kumar, M. Alemu, M. Berry, "EMG Based Voice Recognition", in Proc. of IEEE Conf. on Intelligent Sensors, Sensor Network and Information Processing, pp. 593-597, Melbourne, Australia, Dec 2004.
  4. J. F. Gemmeke, T. Virtanen, A. Hurmalainen, "Exemplar-Based Sparse Representations for Noise Robust Automatic Speech Recognition", IEEE Trans. Audio, Speech and Language Processing, Vol. 19, no. 7, Sep. 2011.
  5. T. Heistermann, M. Janke, M. Wand, T. Schultz, "Spatial Artifact Detection for Multi-Channel EMG-Based Speech Recognition", Internatinal Conf. on Bio-inspired Systems and Signal Processing, pp. 189-196, Angers, France, Mar 2014.
  6. H. Manabe, Z. Zhang, "Multi-stream HMM for EMG-based speech recognition", in Proc. of IEEE Conf. on Engineering in Medicine and Biology Society, pp. 4389-4392, San Francisco, CA, Jun 2004.
  7. Y. Deng, R. Patel, J. T. Heaton, G. Colby, L. D. Gilmore, J. Cabrera, S. H. Roy, C. J. D. Luca, G. S. Meltzner, "Disordered speech recognition using acoustic and sEMG signals", INTERSPEECH 2009, pp. 644-647, Brighton, UK, Sep 2009.
  8. C. Jorgensen, S. Dusan, "Speech interfaces based upon surface electromyography", Speech Communication, Vol. 20, no. 4, pp. 354-366, Apr 2010.
  9. A.D.C. Chan, K. Englehart, B, Hudgins, D.F. Lovely, "Hidden Markov Model Classification of Myoelectric Signals in Speech", IEEE Trans. Engineering in Medicine and Biology Magazine, Vol. 21, no. 4, pp. 143-146, Sep 2002. https://doi.org/10.1109/MEMB.2002.1044184
  10. H. Yong, "A Typological Study on Korean Vowel Systems", Language and Linguistics, pp. 175-200, Vol. 61, Nov 2013.
  11. A. Phinyomark, S. Hirunviriya, C. Limsakul, P. Phukpattaranont, "Evaluation of EMG Feature Extraction for Hand Movement Recognition Based on Euclidean Distance and Standard Deviation", in Proc. of IEEE Conf. on ECTI, pp.856-860, Chiang Mai, Thailand, May 2010.
  12. E. Scheme, K. Englehart, "On the Robustness of EMG Features for Pattern Recognition Based Myoelectric Control; A Multi-Dataset Comparison", in Proc. of IEEE Conf. on EMBS, pp.650-653, Chicago, USA, Aug 2014.
  13. B-H. Lee, J-H. Ryu, M-R. Lee, S-H. Kim, M. Z. Uddin, D-H. Kim, "Monophthong recognition using feature and muscle selection based on facial surface EMG signals", in Proc. of The IEEK Conf. on Summer Conference, pp. 933-936, Jeju, Korea, Jun 2015.
  14. N. Srisuwan, P. phukpattaranont, C. Limsakul, "Three Steps of Neuron Network Classification for EMG-based Thai Tones Speech Recognition", in Proc. of IEEE Conf. on ECTI, pp. 1-6, Krabi, Thailand, May 2013.
  15. E. Lopez-Larraz, O. M. Mozos, J. M. Antelis, J. Minguez, "Syllable-Based Speech Recognition Using EMG", in Proc. of IEEE Conf. on EMBS, pp. 4699-4702, Buenos Aires, Argentina, Aug 2010.