This preprint is under consideration at EURASIP Journal on Advances in Signal Processing. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Research
Youming Wang
Xi'an University of Posts and Telecommunications
Corresponding Author
ORCiD: https://orcid.org/0000-0002-5184-2705
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Speech is easily interfered by the external environment in reality, which will lose the important features. Deep learning method has become the mainstream method of speech enhancement because of its superior potential in complex nonlinear mapping problems. However, there are some problems are exist such as the deficiency for the learning the important information from previous time steps and long-term event dependencies. Due to the lack of the correlation in the same layer of Deep Neural Networks (DNNs), which is an existing typical intelligent deep model of speech signal, it is difficult to capture the long-term dependence between the time-series data. To overcome this problem, we propose a novel speech enhancement method from fused features based on deep neural network and gated recurrent unit network. The method takes advantage of both deep neural network and recurrent neural network to reduce the number of parameters and simultaneously improve speech quality and intelligibility. Firstly, DNN with multiple hidden layers is used to learn the mapping relationship between the logarithmic power spectrum (LPS) features of noisy speech and clean speech. Secondly, the LPS feature of the deep neural network is fused with the noisy speech as the input of gated recurrent unit (GRU) network to compensate the missing context information. Finally, GRU network is performed to learn the mapping relationship between LPS features and log power spectrum features of clean speech spectrum. Experimental results demonstrate that the PESQ, SSNR and STOI of the proposed algorithm are improved by 30.72%, 39.84% and 5.53% respectively compared with the noise signal under the condition of matched noise. Under the condition of unmatched noise, the PESQ and STOI of the algorithm are improved by 23.8% and 37.36% respectively. The advantage of the proposed method is that it uses of the key information of features to suppress noise in both matched and unmatched noise cases and the proposed method outperforms other common methods in speech enhancement.
Keywords
speech enhancement, deep neural network, gated recurrent unit, feature fusion, speech quality
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
The full text of this article is available to read as a PDF.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 1
Posted 14 Jun, 2021
No community comments so far
Editorial decision: Major revision
On 28 Aug, 2021
Review #2 received
Received 01 Aug, 2021
Review #1 received
Received 22 Jun, 2021
Reviewer #3 agreed
On 17 Jun, 2021
Reviewer #2 agreed
On 15 Jun, 2021
Reviewers invited
Invitations sent on 15 Jun, 2021
Reviews received
Received 15 Jun, 2021
Reviewer #1 agreed
On 15 Jun, 2021
Submission checks complete
On 26 May, 2021
Editor invited
On 26 May, 2021
Editor assigned
On 26 May, 2021
First submitted
On 23 May, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
This preprint is under consideration at EURASIP Journal on Advances in Signal Processing. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research
Youming Wang
Xi'an University of Posts and Telecommunications
Corresponding Author
ORCiD: https://orcid.org/0000-0002-5184-2705
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 1
Posted 14 Jun, 2021
No community comments so far
Editorial decision: Major revision
On 28 Aug, 2021
Review #2 received
Received 01 Aug, 2021
Review #1 received
Received 22 Jun, 2021
Reviewer #3 agreed
On 17 Jun, 2021
Reviewer #2 agreed
On 15 Jun, 2021
Reviewers invited
Invitations sent on 15 Jun, 2021
Reviews received
Received 15 Jun, 2021
Reviewer #1 agreed
On 15 Jun, 2021
Submission checks complete
On 26 May, 2021
Editor invited
On 26 May, 2021
Editor assigned
On 26 May, 2021
First submitted
On 23 May, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Speech is easily interfered by the external environment in reality, which will lose the important features. Deep learning method has become the mainstream method of speech enhancement because of its superior potential in complex nonlinear mapping problems. However, there are some problems are exist such as the deficiency for the learning the important information from previous time steps and long-term event dependencies. Due to the lack of the correlation in the same layer of Deep Neural Networks (DNNs), which is an existing typical intelligent deep model of speech signal, it is difficult to capture the long-term dependence between the time-series data. To overcome this problem, we propose a novel speech enhancement method from fused features based on deep neural network and gated recurrent unit network. The method takes advantage of both deep neural network and recurrent neural network to reduce the number of parameters and simultaneously improve speech quality and intelligibility. Firstly, DNN with multiple hidden layers is used to learn the mapping relationship between the logarithmic power spectrum (LPS) features of noisy speech and clean speech. Secondly, the LPS feature of the deep neural network is fused with the noisy speech as the input of gated recurrent unit (GRU) network to compensate the missing context information. Finally, GRU network is performed to learn the mapping relationship between LPS features and log power spectrum features of clean speech spectrum. Experimental results demonstrate that the PESQ, SSNR and STOI of the proposed algorithm are improved by 30.72%, 39.84% and 5.53% respectively compared with the noise signal under the condition of matched noise. Under the condition of unmatched noise, the PESQ and STOI of the algorithm are improved by 23.8% and 37.36% respectively. The advantage of the proposed method is that it uses of the key information of features to suppress noise in both matched and unmatched noise cases and the proposed method outperforms other common methods in speech enhancement.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
The full text of this article is available to read as a PDF.
Loading...