最小方差无失真响应（MVDR）波束形成器对基于语音增强的助听器智能手机应用的影响。
Influence of MVDR beamformer on a Speech Enhancement based Smartphone application for Hearing Aids.
作者信息
Shankar Nikhil, Kucuk Abdullah, Reddy Chandan K A, Bhat Gautam S, Panahi Issa M S
出版信息
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:417-420. doi: 10.1109/EMBC.2018.8512369.
Abstract
This paper presents the minimum variance distortionless response (MVDR) beamformer combined with a Speech Enhancement (SE) gain function as a real-time application running on smartphones that work as an assistive device to Hearing Aids. It has been shown that beamforming techniques improve the Signal to Noise Ratio (SNR) in noisy conditions. In the proposed algorithm, MVDR beamformer is used as an SNR booster for the SE method. The proposed SE gain is based on the Log-Spectral Amplitude estimator to improve the speech quality in the presence of different background noises. Objective evaluation and intelligibility measures support the theoretical analysis and show significant improvements of the proposed method in comparison with existing methods. Subjective test results show the effectiveness of the application in real-world noisy conditions at SNR levels of -5 dB, 0 dB, and 5 dB.
摘要
本文介绍了一种结合语音增强（SE）增益函数的最小方差无失真响应（MVDR）波束形成器，它作为一种在智能手机上运行的实时应用程序，可作为助听器的辅助设备。研究表明，波束形成技术在嘈杂环境中可提高信噪比（SNR）。在所提出的算法中，MVDR波束形成器用作SE方法的SNR增强器。所提出的SE增益基于对数谱幅度估计器，以在存在不同背景噪声的情况下提高语音质量。客观评估和可懂度测量支持理论分析，并表明与现有方法相比，所提出的方法有显著改进。主观测试结果表明，该应用在-5 dB、0 dB和5 dB的SNR水平下，在现实世界嘈杂环境中是有效的。
相似文献
1
Influence of MVDR beamformer on a Speech Enhancement based Smartphone application for Hearing Aids.最小方差无失真响应（MVDR）波束形成器对基于语音增强的助听器智能手机应用的影响。
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:417-420. doi: 10.1109/EMBC.2018.8512369.
2
Real-time dual-channel speech enhancement by VAD assisted MVDR beamformer for hearing aid applications using smartphone.使用智能手机的助听器应用中，基于语音活动检测辅助的最小方差无失真响应波束形成器的实时双通道语音增强
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:952-955. doi: 10.1109/EMBC44109.2020.9175212.
3
Two microphones spectral-coherence based speech enhancement for hearing aids using smartphone as an assistive device.基于两个麦克风频谱相干性的助听器语音增强，利用智能手机作为辅助设备。
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:3670-3673. doi: 10.1109/EMBC.2016.7591524.
4
Smartphone based real-time super Gaussian single microphone Speech Enhancement to improve intelligibility for hearing aid users using formant information.基于智能手机的实时超高斯单麦克风语音增强技术，利用共振峰信息提高助听器用户的语音清晰度。
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:5503-5506. doi: 10.1109/EMBC.2018.8513674.
5
Formant Frequency-based Speech Enhancement Technique to improve Intelligibility for hearing aid users with smartphone as an assistive device.基于共振峰频率的语音增强技术，以提高使用智能手机作为辅助设备的助听器用户的语音清晰度。
Health Innov Point Care Conf. 2017 Nov;2017:32-35. doi: 10.1109/hic.2017.8227577. Epub 2017 Dec 21.
6
Smartphone-based real-time speech enhancement for improving hearing aids speech perception.基于智能手机的实时语音增强技术，用于改善助听器的语音感知能力。
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:5885-5888. doi: 10.1109/EMBC.2016.7592067.
7
Smartphone-based single-channel speech enhancement application for hearing aids.基于智能手机的单通道语音增强助听器应用。
J Acoust Soc Am. 2021 Sep;150(3):1663. doi: 10.1121/10.0006045.
8
Smartphone-based noise adaptive speech enhancement for hearing aid applications.用于助听器应用的基于智能手机的噪声自适应语音增强技术。
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:85-88. doi: 10.1109/EMBC.2016.7590646.
9
Speech Intelligibility and Spatial Release From Masking Improvements Using Spatial Noise Reduction Algorithms in Bimodal Cochlear Implant Users.双耳植入式助听设备中空间降噪算法对语音可懂度和掩蔽释放空间的改善。
Trends Hear. 2021 Jan-Dec;25:23312165211005931. doi: 10.1177/23312165211005931.
10
Efficient two-microphone speech enhancement using basic recurrent neural network cell for hearing and hearing aids.使用基本递归神经网络单元实现用于听力和助听器的高效双麦克风语音增强
J Acoust Soc Am. 2020 Jul;148(1):389. doi: 10.1121/10.0001600.
引用本文的文献
1
CONVOLUTIONAL RECURRENT NEURAL NETWORK BASED DIRECTION OF ARRIVAL ESTIMATION METHOD USING TWO MICROPHONES FOR HEARING STUDIES.基于卷积递归神经网络的用于听力研究的双麦克风到达方向估计方法
IEEE Int Workshop Mach Learn Signal Process. 2020 Sep;2020. doi: 10.1109/mlsp49062.2020.9231693. Epub 2020 Oct 20.
2
Real-time single-channel deep neural network-based speech enhancement on edge devices.基于实时单通道深度神经网络的边缘设备语音增强技术。
Interspeech. 2020 Oct;2020:3281-3285. doi: 10.21437/Interspeech.2020-1901.
3
Real-time dual-channel speech enhancement by VAD assisted MVDR beamformer for hearing aid applications using smartphone.使用智能手机的助听器应用中，基于语音活动检测辅助的最小方差无失真响应波束形成器的实时双通道语音增强
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:952-955. doi: 10.1109/EMBC44109.2020.9175212.
4
Design and Integration of Alert Signal Detector and Separator for Hearing Aid Applications.用于助听器应用的警报信号检测器与分离器的设计与集成
IEEE Access. 2020;8:106296-106309. doi: 10.1109/access.2020.2999546.
5
Real-time Convolutional Neural Network based Speech Source Localization on Smartphone.基于实时卷积神经网络的智能手机语音源定位
IEEE Access. 2019;7:169969-169978. doi: 10.1109/access.2019.2955049. Epub 2019 Nov 22.
6
Efficient two-microphone speech enhancement using basic recurrent neural network cell for hearing and hearing aids.使用基本递归神经网络单元实现用于听力和助听器的高效双麦克风语音增强
J Acoust Soc Am. 2020 Jul;148(1):389. doi: 10.1121/10.0001600.
7
Direction of arrival estimation using deep neural network for hearing aid applications using smartphone.使用深度神经网络进行到达方向估计以用于智能手机助听器应用。
Proc Meet Acoust. 2019 Dec 2;39(1). doi: 10.1121/2.0001256. Epub 2020 Jun 22.
8
A Real-Time Convolutional Neural Network Based Speech Enhancement for Hearing Impaired Listeners Using Smartphone.一种基于实时卷积神经网络的、使用智能手机的听力受损者语音增强方法。
IEEE Access. 2019;7:78421-78433. doi: 10.1109/access.2019.2922370. Epub 2019 Jun 12.
本文引用的文献
1
Formant Frequency-based Speech Enhancement Technique to improve Intelligibility for hearing aid users with smartphone as an assistive device.基于共振峰频率的语音增强技术，以提高使用智能手机作为辅助设备的助听器用户的语音清晰度。
Health Innov Point Care Conf. 2017 Nov;2017:32-35. doi: 10.1109/hic.2017.8227577. Epub 2017 Dec 21.
2
An individualized super-Gaussian single microphone Speech Enhancement for hearing aid users with smartphone as an assistive device.一种以智能手机为辅助设备的针对助听器用户的个性化超高斯单麦克风语音增强技术。
IEEE Signal Process Lett. 2017 Nov;24(11):1601-1605. doi: 10.1109/LSP.2017.2750979. Epub 2017 Sep 11.
3
Two microphones spectral-coherence based speech enhancement for hearing aids using smartphone as an assistive device.基于两个麦克风频谱相干性的助听器语音增强，利用智能手机作为辅助设备。
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:3670-3673. doi: 10.1109/EMBC.2016.7591524.
4
An evaluation of objective measures for intelligibility prediction of time-frequency weighted noisy speech.基于时频加权噪声语音可懂度预测的客观测量评估。
J Acoust Soc Am. 2011 Nov;130(5):3013-27. doi: 10.1121/1.3641373.
5
Factors influencing intelligibility of ideal binary-masked speech: implications for noise reduction.影响理想二元掩蔽语音可懂度的因素：对降噪的启示
J Acoust Soc Am. 2008 Mar;123(3):1673-82. doi: 10.1121/1.2832617.
6
The future of hearing aid technology.助听器技术的未来。
Trends Amplif. 2007 Mar;11(1):31-45. doi: 10.1177/1084713806298004.
Zotero 插件