A Dual Target Neural Network Method for Speech Enhancement

Page view(s)
29
Checked on Apr 12, 2024
A Dual Target Neural Network Method for Speech Enhancement
Title:
A Dual Target Neural Network Method for Speech Enhancement
Journal Title:
2023 International Conference on Asian Language Processing (IALP)
Keywords:
Publication Date:
12 December 2023
Citation:
You, C., Dong, M., & Wang, L. (2023, November 18). A Dual Target Neural Network Method for Speech Enhancement. 2023 International Conference on Asian Language Processing (IALP). https://doi.org/10.1109/ialp61005.2023.10336989
Abstract:
In this paper, we introduce a neural network based speech enhancement method for heavy noisy scenarios. Comprising bidirectional long-short term memory (BLSTM), convolutional neural network (CNN) and deep feedforward neural network (DNN), a neural network architecture with a novel dual target scheme is proposed. The dual target scheme leverages the speech features from both linear and Mel spectral domains in order to retrieve very weak speech spectrum hidden in heavy noise. Experiments show that our proposed neural network architecture outperforms many traditional enhancement methods in terms of objective distortion measure and quality measure.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2159-1970
Files uploaded:

File Size Format Action
enhancespeech-ialp2023-revised-aceepted-v2.pdf 1.30 MB PDF Request a copy