Clinical evaluation of the performance of a blind source separation algorithm combining beamforming and independent component analysis in hearing aid use

Authors:
Kyoung Won Nam;Yoon Sang Ji;Jonghee Han;Sangmin Lee;Dongwook Kim;Sung Hwa Hong;Dong Pyo Jang;In Young Kim
Affiliations:
Department of Biomedical Engineering, Hanyang University, Seoul 133-791, South Korea;Department of Biomedical Engineering, Hanyang University, Seoul 133-791, South Korea;Bio and Health Lab, Samsung Advanced Institute of Technology, Yongin 446-712, South Korea;Department of Electronic Engineering, Inha University, Incheon 402-751, South Korea;Bio and Health Lab, Samsung Advanced Institute of Technology, Yongin 446-712, South Korea;Department of Otolaryngology-Head and Neck Surgery, Samsung Medical Center, Seoul 135-710, South Korea;Department of Biomedical Engineering, Hanyang University, Seoul 133-791, South Korea;Department of Biomedical Engineering, Hanyang University, Seoul 133-791, South Korea
Venue:
Speech Communication
Year:
2013

Citing 14
Cited 1

Assessment for automatic speech recognition II: NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems

Speech Communication - Special issue on speech processing in adverse conditions
Phonetic analyses of word and segment variation using the TIMIT corpus of American English

Speech Communication
Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources

Neural Computation
Speech enhancement based on a priori signal to noise estimation

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
Blind source separation combining frequency-domain ICA and beamforming

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 05
Blind source separation combining independent component analysis and beamforming

EURASIP Journal on Applied Signal Processing
Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

Speech Communication
Spatial efficiency of blind source separation based on decorrelation - subjective and objective assessment

Speech Communication
Blind separation combined frequency invariant beamforming and ICA for far-field broadband acoustic signals

ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Adaptive null-forming scheme in digital hearing aids

IEEE Transactions on Signal Processing
A new independent component analysis for speech recognition and separation

IEEE Transactions on Audio, Speech, and Language Processing
Blind source separation based on a fast-convergence algorithm combining ICA and beamforming

IEEE Transactions on Audio, Speech, and Language Processing
Face recognition with lattice independent component analysis and extreme learning machines

Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special Issue on Extreme Learning Machines (ELM 2011) Hangzhou, China, December 6 – 8, 2011
A two-stage Independent Component Analysis-based method for blind detection in CDMA systems

Digital Signal Processing

Modified segmental signal-to-noise ratio reflecting spectral masking effect for evaluating the performance of hearing aid algorithms

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

There have been several reports on improved blind source separation algorithms that combine beamforming and independent component analysis. However, none of the prior reports verified the clinical efficacy of such combinational algorithms in real hearing aid situations. In the current study, we evaluated the clinical efficacy of such a combinational algorithm using the mean opinion score and speech recognition threshold tests in various types of real-world hearing aid situations involving environmental noise. Parameters of the testing algorithm were adjusted to match the geometric specifications of the real behind-the-ear type hearing aid housing. The study included 15 normal-hearing volunteers and 15 hearing-impaired patients. Experimental results demonstrated that the testing algorithm improved the speech intelligibility of all of the participants in noisy environments, and the clinical efficacy of the combinational algorithm was superior to either the beamforming or independent component analysis algorithms alone. Despite the computational complexity of the testing algorithm, our experimental results and the rapid enhancement of hardware technology indicate that the testing algorithm has the potential to be applied to real hearing aids in the near future, thereby improving the speech intelligibility of hearing-impaired patients in noisy environments.