Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask

A deep learning speech enhancement algorithm based on dynamic hybrid feature and adaptive mask and DSP implementation is proposed in this paper, which solves the problem of feature loss and improves the performance of speech enhancement. The dynamic features incorporate the log Mel power spectrum, M...

Full description

Saved in:
Bibliographic Details
Main Authors: Jie Yang, Yachun Tang
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2022/7287072
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832563504656154624
author Jie Yang
Yachun Tang
author_facet Jie Yang
Yachun Tang
author_sort Jie Yang
collection DOAJ
description A deep learning speech enhancement algorithm based on dynamic hybrid feature and adaptive mask and DSP implementation is proposed in this paper, which solves the problem of feature loss and improves the performance of speech enhancement. The dynamic features incorporate the log Mel power spectrum, Mel cepstral coefficients, and Multiresolution Auditory Cepstral Coefficients (MRACC) and capture the speech transient information by deriving the derivatives to comprehensively represent the nonlinear structure of speech and reduce distortion. To make the system improve the speech quality while reducing the speech distortion as much as possible, a soft mask that can be adaptively adjusted considering the signal-to-noise ratio information is proposed, which can be automatically adjusted according to the different speech signal-to-noise ratio information to obtain the mask value under the corresponding signal-to-noise ratio conditions, and phase difference information that can improve the speech intelligibility is incorporated in it. Then, an improved deep neural network model is designed to effectively improve the speech enhancement performance. Finally, the hardware and algorithm software design of the DSP-based speech enhancement system is given. Experimental simulations are carried out for multiple voices in different noise backgrounds. The experimental results indicate that the performance indexes of the proposed method are significantly improved compared with the existing speech enhancement methods, which verifies the feasibility and superiority of the proposed method.
format Article
id doaj-art-8a67b35efa4c49168c8f85f5915f858b
institution Kabale University
issn 2090-0155
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-8a67b35efa4c49168c8f85f5915f858b2025-02-03T01:20:00ZengWileyJournal of Electrical and Computer Engineering2090-01552022-01-01202210.1155/2022/7287072Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive MaskJie Yang0Yachun Tang1School of Electronics and Information EngineeringSchool of Electronics and Information EngineeringA deep learning speech enhancement algorithm based on dynamic hybrid feature and adaptive mask and DSP implementation is proposed in this paper, which solves the problem of feature loss and improves the performance of speech enhancement. The dynamic features incorporate the log Mel power spectrum, Mel cepstral coefficients, and Multiresolution Auditory Cepstral Coefficients (MRACC) and capture the speech transient information by deriving the derivatives to comprehensively represent the nonlinear structure of speech and reduce distortion. To make the system improve the speech quality while reducing the speech distortion as much as possible, a soft mask that can be adaptively adjusted considering the signal-to-noise ratio information is proposed, which can be automatically adjusted according to the different speech signal-to-noise ratio information to obtain the mask value under the corresponding signal-to-noise ratio conditions, and phase difference information that can improve the speech intelligibility is incorporated in it. Then, an improved deep neural network model is designed to effectively improve the speech enhancement performance. Finally, the hardware and algorithm software design of the DSP-based speech enhancement system is given. Experimental simulations are carried out for multiple voices in different noise backgrounds. The experimental results indicate that the performance indexes of the proposed method are significantly improved compared with the existing speech enhancement methods, which verifies the feasibility and superiority of the proposed method.http://dx.doi.org/10.1155/2022/7287072
spellingShingle Jie Yang
Yachun Tang
Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask
Journal of Electrical and Computer Engineering
title Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask
title_full Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask
title_fullStr Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask
title_full_unstemmed Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask
title_short Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask
title_sort research and dsp implementation of speech enhancement technology based on dynamic mixed features and adaptive mask
url http://dx.doi.org/10.1155/2022/7287072
work_keys_str_mv AT jieyang researchanddspimplementationofspeechenhancementtechnologybasedondynamicmixedfeaturesandadaptivemask
AT yachuntang researchanddspimplementationofspeechenhancementtechnologybasedondynamicmixedfeaturesandadaptivemask