Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction
This paper proposes a novel technique to improve a spectral statistical filter for speech enhancement, to be applied in wearable hearing devices such as hearing aids. The proposed method is implemented considering a 32-channel uniform polyphase discrete Fourier transform filter bank, for which the o...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/20/5751 |
_version_ | 1797551438543454208 |
---|---|
author | Seon Man Kim |
author_facet | Seon Man Kim |
author_sort | Seon Man Kim |
collection | DOAJ |
description | This paper proposes a novel technique to improve a spectral statistical filter for speech enhancement, to be applied in wearable hearing devices such as hearing aids. The proposed method is implemented considering a 32-channel uniform polyphase discrete Fourier transform filter bank, for which the overall algorithm processing delay is 8 ms in accordance with the hearing device requirements. The proposed speech enhancement technique, which exploits the concepts of both non-negative sparse coding (NNSC) and spectral statistical filtering, provides an online unified framework to overcome the problem of residual noise in spectral statistical filters under noisy environments. First, the spectral gain attenuator of the statistical Wiener filter is obtained using the a priori signal-to-noise ratio (SNR) estimated through a decision-directed approach. Next, the spectrum estimated using the Wiener spectral gain attenuator is decomposed by applying the NNSC technique to the target speech and residual noise components. These components are used to develop an NNSC-based Wiener spectral gain attenuator to achieve enhanced speech. The performance of the proposed NNSC–Wiener filter was evaluated through a perceptual evaluation of the speech quality scores under various noise conditions with SNRs ranging from -5 to 20 dB. The results indicated that the proposed NNSC–Wiener filter can outperform the conventional Wiener filter and NNSC-based speech enhancement methods at all SNRs. |
first_indexed | 2024-03-10T15:44:44Z |
format | Article |
id | doaj.art-c881c73b7a4e461e92db7a0eb4042950 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T15:44:44Z |
publishDate | 2020-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-c881c73b7a4e461e92db7a0eb40429502023-11-20T16:33:49ZengMDPI AGSensors1424-82202020-10-012020575110.3390/s20205751Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise ReductionSeon Man Kim0Korea Photonics Technology Institute, Gwangju 61007, KoreaThis paper proposes a novel technique to improve a spectral statistical filter for speech enhancement, to be applied in wearable hearing devices such as hearing aids. The proposed method is implemented considering a 32-channel uniform polyphase discrete Fourier transform filter bank, for which the overall algorithm processing delay is 8 ms in accordance with the hearing device requirements. The proposed speech enhancement technique, which exploits the concepts of both non-negative sparse coding (NNSC) and spectral statistical filtering, provides an online unified framework to overcome the problem of residual noise in spectral statistical filters under noisy environments. First, the spectral gain attenuator of the statistical Wiener filter is obtained using the a priori signal-to-noise ratio (SNR) estimated through a decision-directed approach. Next, the spectrum estimated using the Wiener spectral gain attenuator is decomposed by applying the NNSC technique to the target speech and residual noise components. These components are used to develop an NNSC-based Wiener spectral gain attenuator to achieve enhanced speech. The performance of the proposed NNSC–Wiener filter was evaluated through a perceptual evaluation of the speech quality scores under various noise conditions with SNRs ranging from -5 to 20 dB. The results indicated that the proposed NNSC–Wiener filter can outperform the conventional Wiener filter and NNSC-based speech enhancement methods at all SNRs.https://www.mdpi.com/1424-8220/20/20/5751hearing devicehearing aidspeech enhancementWiener filterresidual noisenon-negative sparse coding |
spellingShingle | Seon Man Kim Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction Sensors hearing device hearing aid speech enhancement Wiener filter residual noise non-negative sparse coding |
title | Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction |
title_full | Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction |
title_fullStr | Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction |
title_full_unstemmed | Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction |
title_short | Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction |
title_sort | wearable hearing device spectral enhancement driven by non negative sparse coding based residual noise reduction |
topic | hearing device hearing aid speech enhancement Wiener filter residual noise non-negative sparse coding |
url | https://www.mdpi.com/1424-8220/20/20/5751 |
work_keys_str_mv | AT seonmankim wearablehearingdevicespectralenhancementdrivenbynonnegativesparsecodingbasedresidualnoisereduction |