Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

The research on the MEMS device improvement which is necessary for the noise environment in the speech recognition rate improvement

잡음 환경에서 음성 인식률 향상에 필요한 MEMS 장치 개발에 관한 연구

  • Yang, Ki-Woong (Department of Computer Engineering, Kwangwoon University) ;
  • Lee, Hyung-keun (Department of Computer Engineering, Kwangwoon University)
  • Received : 2018.10.29
  • Accepted : 2018.12.04
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

When the input sound is mixed voice and sound, it can be seen that the voice recognition rate is lowered due to the noise, and the speech recognition rate is improved by improving the MEMS device which is the H / W device in order to overcome the S/W processing limit. The MEMS microphone device is a device for inputting voice and is implemented in various shapes and used. Conventional MEMS microphones generally exhibit excellent performance, but in a special environment such as noise, there is a problem that the processing performance is deteriorated due to a mixture of voice and sound. To overcome these problems, we developed a newly designed MEMS device that can detect the voice characteristics of the initial input device.

입력된 소리가 음성과 음향이 혼재된 경우 잡음의 영향으로 음성 인식률이 저하됨을 알 수 있으며 S/W적 처리 한계를 극복코자 H/W 장치인 MEMS 장치를 개발하여 음성 인식률을 향상시켰다. MEMS 마이크로폰 장치는 음성을 입력하는 장치로서 다양한 모양으로 구현되어 사용된다. 기존 MEMS 마이크로폰은 일반적으로 우수한 성능을 발휘하나 잡음 과 같은 특수 환경에선 음성과 음향이 혼재되어 처리 성능이 저하되는 문제점이 발생됨을 알 수 있었다. 이러한 문제점을 개선코자 초기 입력장치에 음성 특성을 구분하여 검출할 수 있는 신규 고안된 MEMS 장치를 사용하여 향상시켰다.

Keywords

HOJBC0_2018_v22n12_1659_f0001.png 이미지

Fig. 1 Improved MEMS device

HOJBC0_2018_v22n12_1659_f0002.png 이미지

Fig. 2 Acoustic and electrical relationship

HOJBC0_2018_v22n12_1659_f0003.png 이미지

Fig. 3 Experiment environment

HOJBC0_2018_v22n12_1659_f0004.png 이미지

Fig. 4 perpendicular test environment

HOJBC0_2018_v22n12_1659_f0005.png 이미지

Fig. 5 ×1 horizontal test environment

HOJBC0_2018_v22n12_1659_f0006.png 이미지

Fig. 6 ×3 horizontal test environment block diagram

HOJBC0_2018_v22n12_1659_f0007.png 이미지

Fig. 7 normal test environment block diagram

HOJBC0_2018_v22n12_1659_f0008.png 이미지

Fig. 8 Improved artificial intelligence(single layer1-1)

HOJBC0_2018_v22n12_1659_f0009.png 이미지

Fig. 9 Improved artificial intelligence(single layer1-2)

HOJBC0_2018_v22n12_1659_f0010.png 이미지

Fig. 10 Improved artificial intelligence(Multi layer1-1)

HOJBC0_2018_v22n12_1659_f0011.png 이미지

Fig. 11 Improved artificial intelligence(Multi layer1-2)

Table. 1 The kind of MEMS

HOJBC0_2018_v22n12_1659_t0001.png 이미지

Table. 2 Features of MEMS microphones(Example)

HOJBC0_2018_v22n12_1659_t0002.png 이미지

Table. 3 Speech recognition rates

HOJBC0_2018_v22n12_1659_t0003.png 이미지

Table. 4 frequency recognition number

HOJBC0_2018_v22n12_1659_t0004.png 이미지

Table. 5 The consonant system table 1

HOJBC0_2018_v22n12_1659_t0005.png 이미지

Table. 6 The consonant system table 2

HOJBC0_2018_v22n12_1659_t0006.png 이미지

References

  1. Electronic Ports N Components (2018, November) , The MEMS market 'crustal movements' ...2,015-2,017 year MEMS market analysis [Internet]. Available: http://www.epnc.co.kr/news/articleView.html?idxno=80494, Nov. 2018.
  2. K. W. Yang et al, Microphone and Method for processing Acoustic, KR Patent 1017834320000 to K. W. Yang, Patent and Trademark Office, Daejeon, 2017.
  3. Y. Yoon, "Some Studies on the characteristics of Musical Instrument Strings. - In the Case of Korean Traditional Musical Instrument -," Journal of the National Center for Korean Traditional Performing Art, vol. 12, no. 14, pp. 215-275, Apr. 2000.
  4. Physics for Everyone, The wave equation induction [Internet], Available : http://phy64ev1.tistory.com/6, July 2017.
  5. K. W. Yang, "An Implementation of speech Recognition of Bus-Subway System Using GIS base on the Urban," Kwangwoon University, M.S Thesis, Feb. 2000.
  6. J. Xu, Y. J. Si, J. L. Pan, and Y. H. Yan., "Automatic allophone deriving for korean speech recognition," 2013 Ninth International Conference on Computational Intelligence and Security, pp. 776-779, Dec. 2013.
  7. S. M. Hwang, B. H. Song, and H. K. Yun, "Korean speech recognition using phonemics for lip-sync animation," 2014 International Conference on Information Science, Electronics and Electrical Engineering, vol. 2, pp. 1011-1014, 2014.
  8. G. Y. Lim, Y. B. Cho, "The Sentence Similarity Measure Using Deep-Learning and Char2Vec," Journal of the Korea Institute of Information and Communication Engineering , vol. 22, no. 10, pp.1300-1306, Oct. 2018. https://doi.org/10.6109/JKIICE.2018.22.10.1300
  9. B. W. Cheon, N. H. Kim, "High Density Impulse Noise Reduction Filter Algorithm using Effective Pixels," Journal of the Korea Institute of Information and Communication Engineering , vol. 22, no. 10, pp.1320-1326, Oct. 2018. https://doi.org/10.6109/JKIICE.2018.22.10.1320
  10. H. M. Jeon, C. S. Bae, and H. G. Yang, "Clutter Suppression Method for Altitude and Mainlobe Clutter In Moving Platform Radar," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 10, pp. 1386-1391, Oct. 2018. https://doi.org/10.6109/JKIICE.2018.22.10.1386

Cited by

  1. Non-verbal Communication and Touchless Activation of a Radio-Controlled Car via Facial Activity Recognition vol.21, pp.6, 2018, https://doi.org/10.1007/s12541-019-00291-x