인공 신경망을 이용한 보청기용 실시간 환경분류 알고리즘
Real Time Environmental Classification Algorithm Using Neural Network for Hearing Aids
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Persons with sensorineural hearing impairment have troubles in hearing at noisy environments because of their deteriorated hearing levels and low-spectral resolution of the auditory system and therefore, they use hearing aids to compensate weakened hearing abilities. Various algorithms for hearing loss compensation and environmental noise reduction have been implemented in the hearing aid; however, the performance of these algorithms vary in accordance with external sound situations and therefore, it is important to tune the operation of the hearing aid appropriately in accordance with a wide variety of sound situations. In this study, a sound classification algorithm that can be applied to the hearing aid was suggested. The proposed algorithm can classify the different types of speech situations into four categories: 1) speech-only, 2) noise-only, 3) speech-in-noise, and 4)music-only. The proposed classification algorithm consists of two sub-parts: a feature extractor and a speech situation classifier. The former extracts seven characteristic features - short time energy and zero crossing rate in the time domain; spectral centroid, spectral flux and spectral roll-off in the frequency domain; mel frequency cepstral coefficients and power values of mel bands - from the recent input signals of two microphones, and the latter classifies the current speech situation. The experimental results showed that the proposed algorithm could classify the kinds of speech situations with an accuracy of over 94.4%. Based on these results, we believe that the proposed algorithm can be applied to the hearing aid to improve speech intelligibility in noisy environments.
Abstract
Persons with sensorineural hearing impairment have troubles in hearing at noisy environments because of their deteriorated hearing levels and low-spectral resolution of the auditory system and therefore, they use hearing aids to compensate weakened hearing abilities. Various algorithms for hearing loss compensation and environmental noise reduction have been implemented in the hearing aid; however, the performance of these algorithms vary in accordance with external sound situations and therefore, it is important to tune the operation of the hearing aid appropriately in accordance with a wide variety of sound situations. In this study, a sound classification algorithm that can be applied to the hearing aid was suggested. The proposed algorithm can classify the different types of speech situations into four categories: 1) speech-only, 2) noise-only, 3) speech-in-noise, and 4)music-only. The proposed classification algorithm consists of two sub-parts: a feature extractor and a speech situation classifier. The former extracts seven characteristic features - short time energy and zero crossing rate in the time domain; spectral centroid, spectral flux and spectral roll-off in the frequency domain; mel frequency cepstral coefficients and power values of mel bands - from the recent input signals of two microphones, and the latter classifies the current speech situation. The experimental results showed that the proposed algorithm could classify the kinds of speech situations with an accuracy of over 94.4%. Based on these results, we believe that the proposed algorithm can be applied to the hearing aid to improve speech intelligibility in noisy environments.
참고문헌 (20)
- A. Duquesnoy, "Effect of a single interfering noise or speech source upon the binaural sentence intelligibility of aged persons", J. Acoust. Soc. Am, 74, pp.739~ (1983)
- J.M. Festen, "Effects of fluctuating noise and interfering speech on the speech-reception threshold for impaired and normal hearing", J. Acoust. Soc. Am, 88, pp.1725~ (1990)
- S. Hygge, "Normalhearing and hearing-impaired subjects' ability to just follow conversation in competing speech, reversed speech, and noise backgrounds", J. Speech and Hearing Research, 35, pp.208~ (1992)
- R. Plomp, "Noise, amplification, and compression : considerations of three main issues in hearing aid design", Ear and Hearing, 15, pp.2~ (1994)
- E. Alexandre, "Two-layer automatic sound classification system for conversation enhancement in hearing aids", Integrated Computer-Aided Engineering, 15, pp.85~94 (2008)
- A. Bugatti, "Audio classification in speech and music : A comparison between a statistical and a neural approach", EURASIP J. Applied Signal Proc, 2002, pp.372~378 (2002)
- C. Freeman, "Audio environment classification for hearing aids", pp.41~44 (2008), Guelph Univ. Press
- M.C. Büchler, "Algorithms for sound classification in hearing instruments", pp.90~91 (2002), Zurich Univ. Press
- R.O. Duda, "Pattern Classification and Scene Analysis 2nd ed" (2000), Wiley-Interscience Press
- B.D. Barkana, "“Environmental Noise Source Classification Using Neural Networks,” in Information Technology", New Generations Seventh International Conference, pp.259~263 (2010)
- P. Dhanalakshmi, "Classification of audio signals using aann and gmm", Applied Soft Computing, 11, pp.716~723 (2011)
- D. Changhong, "Matlab neural network and application" (2005), National Defense Industry Press
- AUDIO SIGNAL CLASSIFICATION, "H. Subramanian", Credit Seminar Report, ~, pp.M. Tech (2004)
- F. Beritelli, "“A pattern recognition system for environmental sound classification based on MFCCs and neural networks,” Signal Proc", Communication Systems 2nd Int. Conf., pp.1~4 (2008)
- S.H. Yook, "Environmental Noise Classification System for Adaptive Noise Reduction Algorithm in Hearing Aids", The Korea Society of Medical & Biological Engineering (2009)
- S.S. Stevens, "A scale for the measurement of the psychological magnitude pitch", J. Acoust. Soc. Am, 8, pp.185~190 (1937)
- M. Büchler, "Sound classification in hearing aids inspired by auditory scene analysis", EURASIP J. Applied Signal Proc, 2005, pp.2991~3002 (2005)
- L.R. Rabiner, "Theory and application of digital signal processing", pp.777~ (1975), Prentice-Hall Inc. Press
- I. Kaastra, "Designing a neural network for forecasting financial and economic time series", Neurocomputing, 10, pp.215~236 (1996)
- J.M. Kates, "Multichannel dynamic-range compression using digital frequency warping", Eurasip J. on Applied Signal Proc, 2005, pp.3003~3014 (2005)