Browse > Article

Robust Speech Recognition Algorithm of Voice Activated Powered Wheelchair for Severely Disabled Person  

Suk, Soo-Young (산업기술종합연구소 정보기술연구부문 음성처리그룹)
Chung, Hyun-Yeol (영남대학교 정보통신공학과)
Publication Information
The Journal of the Acoustical Society of Korea / v.26, no.6, 2007 , pp. 250-258 More about this Journal
Abstract
Current speech recognition technology s achieved high performance with the development of hardware devices, however it is insufficient for some applications where high reliability is required, such as voice control of powered wheelchairs for disabled persons. For the system which aims to operate powered wheelchairs safely by voice in real environment, we need to consider that non-voice commands such as user s coughing, breathing, and spark-like mechanical noise should be rejected and the wheelchair system need to recognize the speech commands affected by disability, which contains specific pronunciation speed and frequency. In this paper, we propose non-voice rejection method to perform voice/non-voice classification using both YIN based fundamental frequency(F0) extraction and reliability in preprocessing. We adopted a multi-template dictionary and acoustic modeling based speaker adaptation to cope with the pronunciation variation of inarticulately uttered speech. From the recognition tests conducted with the data collected in real environment, proposed YIN based fundamental extraction showed recall-precision rate of 95.1% better than that of 62% by cepstrum based method. Recognition test by a new system applied with multi-template dictionary and MAP adaptation also showed much higher accuracy of 99.5% than that of 78.6% by baseline system.
Keywords
Speech recognition; Non-voice rejection; Voice activated powered wheelchair; Inarticulate speech;
Citations & Related Records
연도 인용수 순위
  • Reference
1 D. Ding, R.A. Cooper, 'Electric Powered Wheelchairs,' in IEEE Trans. Control Systems Magazine, 25 22-34, 2005
2 A. de Cheveigne, H. Kawahara, 'YIN, a Fundamental Frequency Estimator for Speech and Music,' in Journal of the Acoustic Society of the America, 111, 2002
3 A. Lee, T. Kawahara and K. Shikano, 'Julius - an Open Source Real-time Large Vocabulary Recognition Engine.' in Proc. European Conference on Speech Communication and Technology, 1691-1694, 2001
4 J. Rouat, Y. C. Liu and D. Morrisette, 'A Pitch Determination and Voiced/Unvoiced Decision Algorithm for Noisy Speech,' in Speech Communication, 21, 1997
5 A. Sasou, H. Kojima, 'Multi-Channel Speech Input System for a Wheelchair,' in Proc. Acoust. Soc. Japan, 2006
6 H. Miyabayashi, T. Funada, 'Pitch extraction and voiced/ unvoiced detection of speech by cross-coupling multi-layered neural network with feedback architecture.' in Journal of Electronics and Communication of Japan, 80 (9) 48-58, 1998
7 K. Sadohara, S.W. Lee and H. Kojima, 'Topic Segmentation Using Kernel Principal Component Analysis for Sub-Phonetic Segments,' Technical Report of IEICE, AI 2004-77, 37-41, 2005
8 K. Giridharan, B.Y. Smolenski and R.E. Yantorno, 'Statistical And Model Based Approach To Unvoiced Speech Detection:' in Proc. ISPACS, 816-821. 2004
9 S.Y. SUK, S.W. Lee, H. Kojima and S. Makino, 'Multi-mixture based PDT-SSS Algorithm for Extension of HMNet Structure,' in Proc. Acoust. Soc. Japan, 2005
10 S. Ahmadi, S. S. Andreas, 'Cepstrum-based Pitch Detection using a New Statistical V/UV Classification Algorithm,' in IEEE Trans. Speech Audio Processing, 7 (3) 333 -339, 1999   DOI   ScienceOn
11 송병섭, 이정현, 박정제, 박희준, 김영남 '화자 독립 방식의 음성인식 칩 및 무선마이크를 이용한 전동 휠체어의 구현' 센서공학회 논문집, 13 (1) 20-26, 2004