상황인지 휴대폰을 위한 음성 코딩 파라미터를 이용한 환경인식 알고리즘
Acoustic Environment Classification Algorithm for Context-aware Mobile Phone
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 논문에서는 상황인지 휴대폰을 위한 음향 데이터를 이용한 환경인식 알고리즘을 3GPP2 Selectable Mode Vocoder (SMV) 코딩 파라미터를 기반으로 제안한다. 휴대폰으로 입력 받은 음향 신호 데이터를 SMV의 부호화 과정에서 자동적으로 추출되는 중요 특징벡터만을 사용하여 Gaussian Mixture Model (GMM)을 구성하고 이를 기반으로 환경인식을 하였다. 실험결과 제안된 코딩 파라미터 기반의 환경인식 알고리즘이 휴대폰의 다양한 음향학적 환경에서 우수한 성능을 보인 것을 알 수 있었다.
Abstract
In this paper, an acoustic environment classification algorithm based on the 3GPP2 selectable mode vocoder (SMV) is proposed for context-aware mobile phones. Classification of the acoustic environment is performed based on a Gaussian mixture model (GMM) using coding parameters of the SMV directly extracted from the encoding process of the acoustic input data in the mobile phone. Experimental results indicate that the proposed environment classification algorithm shows the outstanding performance in various acoustic environments.
참고문헌 (19)
- "Technology for Enabling Awareness"[URL]
- "NOKIA LifeBlog"[URL]
- L. Ma, "''Acoustic environment classification", ACM Transactions on Speech and Language Processing, 3(2), pp.1~22 (2006)
- Y. Toyoda, "''Environmental sound recognition by multilayered neural networks", International Conference on Computer and Information Technology, pp.123~127 (2004)
- L. Couvreur, "''Automatic noise recognition in urban environments based on artificial neural networks and hidden Markov models", InterNoise, Prague, Czech Republic (2004)
- ''Situational awareness from environmental sounds, "N. Sawhney", MIT Media Lab. Technical Report, ~ (1997)
- S. C. Greer, "Standardization of the selectable mode vocoder", IEEE International Conference on Acoustics, Speech and Signal Processing, 통권 : 2, pp.953~956 (2001)
- G. Yang, "The SMV algorithm selected by TIA and 3GPP2 for CDMA applications", IEEE International Conference on Acoustics, Speech and Signal Processing, 통권 : 2, pp.709~712 (2001)
- "3GPP2 Spec., ''Software distribution for selectable mode vocoder (SMV), service option 56, specification,'' 3GPP2-C.R0030-0, v3.0", ~ (2005)
- L. MA, "Environmental noise classification for context aware applications", International Conference on Database and Expert Systems Applications, Lecture Notes in Computer Science, 통권 : 2736, pp.360~370 (2003)
- B. Clarkson, "Auditory context awareness via wearable computing", Perceptual User Interfaces Workshop, pp.37~43 (1998)
- L. R. Rabiner, "Digital processing of speech signal", pp.411~412 (1978), Prentice Hall Inc.
- P. Gaunard, "Automatic classification of environmental noise events by hidden Markov models", IEEE International Conference on Acoustics, Speech and Signal Processing, 통권 : 6, pp.3609~3612 (1998)
- P. Kabal, "The computation of line spectral frequencies using Chebyshev polynomials", IEEE Trans. Acoustics Speech and Signal Processing, ASSP-34(6), pp.1419~1426 (1986)
- C. M. Bishop, "Neural networks for pattern recognition" (1995), Oxford University Press
- R. O. Duda, "Pattern classification" (2001), John Wiley & Sons
- G. Xuan, "EM algorithms of Gaussian mixture model and hidden Markov model", International Conference on Image Processing, 통권 : 1, pp.145~148 (2001)
- A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixed and hidden Markov Models, "J. A. Bilmes", International Computer Science Institute, ~, pp.Technical Report, TR-97-02 (1998)
- A. P. Dempster, "Maximum likelihood from incomplete data via the EM algorithm", Journal of the Royal Statistical Society Series B, 39(1), pp.1~38 (1977)