Improving Speech Quality for Hearing Aid Applications Based on Wiener Filter and Composite of Deep Denoising Autoencoders

Abstract

In hearing aid devices, speech enhancement techniques are a critical component to enable users with hearing loss to attain improved speech quality under noisy conditions. Recently, the deep denoising autoencoder (DDAE) was adopted successfully for recovering the desired speech from noisy observations. However, a single DDAE cannot extract contextual information sufficiently due to the poor generalization in an unknown signal-to-noise ratio (SNR), the local minima, and the fact that the enhanced output shows some residual noise and some level of discontinuity. In this paper, we propose a hybrid approach for hearing aid applications based on two stages: (1) the Wiener filter, which attenuates the noise component and generates a clean speech signal; (2) a composite of three DDAEs with different window lengths, each of which is specialized for a specific enhancement task. Two typical high-frequency hearing loss audiograms were used to test the performance of the approach: Audiogram 1 = (0, 0, 0, 60, 80, 90) and Audiogram 2 = (0, 15, 30, 60, 80, 85). The hearing-aid speech perception index, the hearing-aid speech quality index, and the perceptual evaluation of speech quality were used to evaluate the performance. The experimental results show that the proposed method achieved significantly better results compared with the Wiener filter or a single deep denoising autoencoder alone.

A Review of Fault Diagnosis Methods for Rotating Machinery Using Infrared Thermography

“…The noise reduction algorithm based on transform domain is an indirect noise reduction algorithm, which modifies the transform coefficient value of an image in a certain transform domain. Mean filter [ 55 , 56 , 57 ], median filter [ 58 , 59 ] and Wiener filter [ 60 , 61 ] are classical algorithms for spatial noise reduction. However, the noise reduction principle of the above three image denoising algorithms is to adopt the same noise reduction model for the edge region and the inner region in the image, which will cause the loss of texture feature information while filtering out noises [ 62 ].…”