DOI QR코드

DOI QR Code

A Study on Word Selection Method and Device Improvement for Improving Speech Recognition Rate of Speech-Language-impaired in Severe Noise Environment

심한 소음환경에서 언어장애인 음성 인식률 향상을 위한 단어선정 방법 및 장치 개선에 관한 연구

  • Yang, Ki-Woong (Department of Computer Engineering, Kwangwoon University) ;
  • Lee, Hyung-keun (Department of Computer Engineering, Kwangwoon University)
  • Received : 2019.03.15
  • Accepted : 2019.04.03
  • Published : 2019.05.31

Abstract

Speech recognition rate is lowered even in a noisy environment, and it is difficult for a person with a speech disability or an inconvenient language to use it in a social life. In addition to improving the inconvenience of using the language, 280 words were selected using the word selection method which was improved when the word was selected considering the pronunciation characteristics of the language impaired. The MEMS development device used in the experiment was made considering material, lead wire type, length and direction. We improved the speech recognition rate by using the developed word selection method and the MEMS device developed to improve the speech recognition rate due to incorrect pronunciation and severe noise. The new method of selecting words and the mems device were improved and the results were included.

언어장애인, 언어 사용이 불편한 분들의 경우 조금의 잡음 환경에도 음성인식률이 저하되어 사회 생활시 어려움을 겪게 된다. 언어 사용 시 불편함을 장치로 개선시킴과 동시에, 언어 장애인의 발음 특성을 고려하여 단어 선정 시 자체 개선한 단어 선정 방법을 사용하여 280개 단어를 선정하였다. 실험에 사용된 MEMS 개발 장치는 재질, 유도선 종류, 길이, 방향을 고려하여 제작되었으며 잘못된 발음으로 인한 음성과 심한 소음에서 음성 인식률 향상을 위하여 개발된 MEMS 장치와 개발된 단어 선정 방법을 사용하여 개선시켰다. 개선 방법으론 새로운 단어 선정 방법과 mems 장치를 개선하여 진행하였으며 결과를 포함하였다.

Keywords

HOJBC0_2019_v23n5_555_f0001.png 이미지

Fig. 1 Consonant and vowel position structure

HOJBC0_2019_v23n5_555_f0002.png 이미지

Fig. 2 Configuration step-by-step process

HOJBC0_2019_v23n5_555_f0003.png 이미지

Fig. 3 Improved Variation observation method

HOJBC0_2019_v23n5_555_f0004.png 이미지

Fig. 4 Improved word application example

HOJBC0_2019_v23n5_555_f0005.png 이미지

Fig. 5 Step-specific process diagram

HOJBC0_2019_v23n5_555_f0006.png 이미지

Fig. 6 Improved MEMS device 1

HOJBC0_2019_v23n5_555_f0007.png 이미지

Fig. 7 Improved MEMS device 2

HOJBC0_2019_v23n5_555_f0008.png 이미지

Fig. 8 Experiment environment

HOJBC0_2019_v23n5_555_f0009.png 이미지

Fig. 9 Unmodified Waveform

HOJBC0_2019_v23n5_555_f0010.png 이미지

Fig. 10 Transformation Waveform(metal+(×1) + vertical)

HOJBC0_2019_v23n5_555_f0011.png 이미지

Fig. 11 Transformation Waveform(metal + (×1) + horizontal)

HOJBC0_2019_v23n5_555_f0012.png 이미지

Fig. 12 Transformation Waveform(metal+(×3) + vertical)

HOJBC0_2019_v23n5_555_f0013.png 이미지

Fig. 13 Transformation Waveform(metal + (×3) + horizontal)

HOJBC0_2019_v23n5_555_f0014.png 이미지

Fig. 14 Transformation Waveform(non-metal + stringplace + (×1) + vertical)

HOJBC0_2019_v23n5_555_f0015.png 이미지

Fig. 15 Transformation Waveform(non-metal + stringplace + (×1) + horizontal)

HOJBC0_2019_v23n5_555_f0016.png 이미지

Fig. 16 Transformation Waveform(non-metal + stringplace + (×3) + vertical)

HOJBC0_2019_v23n5_555_f0017.png 이미지

Fig. 17 Transformation Waveform(non-metal + stringplace + (×3) + horizontal)

HOJBC0_2019_v23n5_555_f0018.png 이미지

Fig. 18 Transformation Waveform(non-metal + empty place+ (×1) + vertical)

HOJBC0_2019_v23n5_555_f0019.png 이미지

Fig. 19 Transformation Waveform(on-metal + empty place+ (×1) + horizontal)

HOJBC0_2019_v23n5_555_f0020.png 이미지

Fig. 20 Transformation Waveform(non-metal + emptyplace + (×3) + vertical)

HOJBC0_2019_v23n5_555_f0021.png 이미지

Fig. 21 Transformation Waveform(non-metal + empty place + (×3) + horizontal)

Table. 1 Types and symptoms of language disorders

HOJBC0_2019_v23n5_555_t0001.png 이미지

Table. 2 Decomposition/synthesis process (example)

HOJBC0_2019_v23n5_555_t0002.png 이미지

Table. 3 Supposed Recognition experiment word

HOJBC0_2019_v23n5_555_t0003.png 이미지

Table. 4 Word recognition number (consonant)

HOJBC0_2019_v23n5_555_t0004.png 이미지

Table. 5 Word recognition number (vowel)

HOJBC0_2019_v23n5_555_t0005.png 이미지

Table. 6 Recognition word(non-metal + empty place + (×1) + vertical)

HOJBC0_2019_v23n5_555_t0006.png 이미지

Table. 7 Recognition word(non-metal + empty place + (×1) + horizontal)

HOJBC0_2019_v23n5_555_t0007.png 이미지

Table. 8 Recognition word(non-metal + empty place + (×3) + vertical)

HOJBC0_2019_v23n5_555_t0008.png 이미지

Table. 9 Recognition word(non-metal + empty place + (×3) + horizontal)

HOJBC0_2019_v23n5_555_t0009.png 이미지

Table. 10 Recognition word(non-metal + string place + (×1) + vertical)

HOJBC0_2019_v23n5_555_t0010.png 이미지

Table. 11 Recognition word(non-metal + string place + (×1) + horizontal)

HOJBC0_2019_v23n5_555_t0011.png 이미지

Table. 12 Recognition word(non-metal + string place + (×3) + vertical)

HOJBC0_2019_v23n5_555_t0012.png 이미지

Table. 13 Recognition word(non-metal + string place + (×3) + horizontal)

HOJBC0_2019_v23n5_555_t0013.png 이미지

Table. 14 Recognition word(metal + (×1) + vertical)

HOJBC0_2019_v23n5_555_t0014.png 이미지

Table. 15 Recognition word(metal + (×1) + horizontal)

HOJBC0_2019_v23n5_555_t0015.png 이미지

Table. 16 Recognition word(metal + (×3) + vertical)

HOJBC0_2019_v23n5_555_t0016.png 이미지

Table. 17 Recognition word(metal + (×3) + horizontal)

HOJBC0_2019_v23n5_555_t0017.png 이미지

Table. 18 Unmodified

HOJBC0_2019_v23n5_555_t0018.png 이미지

References

  1. S. I. Kwon, N. H. Kim, "Noise Removal using Modified Switching Filter in Mixed Noise Environments," Journal of the Korea Institute of Information and Communication Engineering, vol. 20 , no. 6, pp. 1216-1220, 2016.
  2. S. E. Ji, W. I. Kim, "Speech Recognition Accuracy Prediction Using Speech Quality Measure," Journal of the Korea Institute of Information and Communication Engineering, vol. 20 , no. 3, pp. 471-476, 2016. https://doi.org/10.6109/jkiice.2016.20.3.471
  3. 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.
  4. C. S. Kim, S. H. Jung, "A MEMS-Based Finger Wearable Computer Input Devices," Journal of the Korea Institute of Information and Communication Engineering, vol. 20 , no. 6, pp. 1103-1108, 2016. https://doi.org/10.6109/jkiice.2016.20.6.1103
  5. S. E. Ji, J. Y. Jo, C. -K. Lee, S. Oh, W. Kim, "Context Recognition Using Environmental Sound for Client Monitoring System," Journal of the Korea Institute of Information and Communication Engineering, vol.19, no. 2, pp. 343-350, 2015. https://doi.org/10.6109/jkiice.2015.19.2.343
  6. J. Y. Lee, L. Kolasani, "Security Based Network for Health Care System," Asia-pacific Journal of Convergent Research Interchange, HSST, ISSN : 2508-9080, vol.1, no.1, Mar (2015), pp. 1-6, http://dx.doi.org/10.21742/APJCRI.2015.03.01
  7. S. H. Sung and P. Z. Khan, "Quantitative and Qualitative Approach for IT Risk Assessment," Asia-pacific Journal of Convergent Research Interchange, HSST, ISSN : 2508-9080, vol.1, no.1, Mar (2015), pp. 29-35, http://dx.doi.org/10.21742/APJCRI.2015.03.04 http://dx.doi.org/10.21742/APJCRI.2015.03.04
  8. D. J. Kim, P. L. Manjusha, "Assessment of Risks in Management Factors," Asia-pacific Journal of Convergent Research Interchange, HSST, ISSN : 2508-9080, vol.1, no.2, Jun (2015), pp. 1-10, http://dx.doi.org/10.21742/APJCRI.2015.06.01