DBSA-Net: Dual Branch Self-Attention Network for Underwater Acoustic Signal Denoising
- 10 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 31 (23299290) , 1851-1865
Abstract
Underwater acoustic signal denoising is a challenging task due to the complexity of the underwater environment. Most of the existing methods cannot effectively cope with the problem of underwater acoustic signal (UWAS) denoising at low signal-to-noise ratios (SNRs). According to the characteristics of UWAS, a novel idea is proposed to simultaneously model latent features from both the time and frequency dimensions of complex-valued spectrum in a dual-branch self-attention network, namely DBSA-Net. In this model, both magnitude and phase information in the complex spectrum are enhanced from different dimensions by two branches. Specifically, DBSA-Net is an encoder-decoder based network with several global-local-self-attention (GL-SA) blocks distributed on dual branches between encoder and decoder. Each GL-SA block incorporates global self-attention and local self-attention to capture distant context and fine-grained local dependencies along the temporal and frequency dimensions. Moreover, we also design an information interaction module between two branches to exchange complementary information. This interaction module together with a merge block fuse features extracted from different dimensions, thus enhancing the capability of our model to learn the target signal features. Extensive experiments are conducted to evaluate our model on a publicly available dataset. Results of the ablation experiments show that the different modules of DBSA-Net play their respective roles in improving denoising performance and are empirically valid. In both the seen ships and unseen ships scenarios, the proposed DBSA-Net outperforms existing approaches by a large margin on various evaluation metrics.Keywords
Funding Information
- National Natural Science Foundation of China (42275170, 61702529)
This publication has 50 references indexed in Scilit:
- Narrowband Chan-Vese model of sonar image segmentation: A adaptive ladder initialization approachApplied Acoustics, 2016
- ShipsEar: An underwater vessel noise databaseApplied Acoustics, 2016
- Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks2015
- Deep neural network based instrument extraction from music2015
- A Regression Approach to Speech Enhancement Based on Deep Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Frequency Domain Based Approach for Denoising of Underwater Acoustic Signal Using EMDJournal of Intelligent Systems, 2013
- The importance of phase in speech enhancementSpeech Communication, 2011
- Wavelet denoising of underwater acoustic dataThe Journal of the Acoustical Society of America, 2002
- Evaluation of a segmental SNR measure as an indicator of the quality of ADPCM coded speechThe Journal of the Acoustical Society of America, 1979
- Suppression of acoustic noise in speech using spectral subtractionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979