Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation
Underwater acoustic signal separation is a key technique for underwater communications. The existing methods are mostly model-based, and cannot accurately characterize the practical underwater acoustic communication environment. They are only suitable for binary signal separation and cannot handle m...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/15/5598 |
| _version_ | 1827624629828583424 |
|---|---|
| author | Jie Chen Chang Liu Jiawu Xie Jie An Nan Huang |
| author_facet | Jie Chen Chang Liu Jiawu Xie Jie An Nan Huang |
| author_sort | Jie Chen |
| collection | DOAJ |
| description | Underwater acoustic signal separation is a key technique for underwater communications. The existing methods are mostly model-based, and cannot accurately characterize the practical underwater acoustic communication environment. They are only suitable for binary signal separation and cannot handle multivariate signal separation. However, recurrent neural networks (RNNs) show a powerful ability to extract the features of temporal sequences. Inspired by this, in this paper, we present a data-driven approach for underwater acoustic signal separation using deep learning technology. We use a bidirectional long short-term memory (Bi-LSTM) approach to explore the features of a time–frequency (T-F) mask, and propose a T-F-mask-aware Bi-LSTM for signal separation. Taking advantage of the sparseness of the T-F image, the designed Bi-LSTM network is able to extract the discriminative features for separation, which further improves the separation performance. In particular, this method breaks through the limitations of the existing methods and not only achieves good results in multivariate separation but also effectively separates signals when they are mixed with 40 dB Gaussian noise signals. The experimental results show that this method can achieve a 97% guarantee ratio (PSR), and the average similarity coefficient of the multivariate signal separation is stable above 0.8 under high noise conditions. It should be noted that our model can only handle known signals such as test signals for calibration. |
| first_indexed | 2024-03-09T12:12:19Z |
| format | Article |
| id | doaj.art-fcf95af9b2754e51ac8fa01dbb256df6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:12:19Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fcf95af9b2754e51ac8fa01dbb256df62023-11-30T22:50:47ZengMDPI AGSensors1424-82202022-07-012215559810.3390/s22155598Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal SeparationJie Chen0Chang Liu1Jiawu Xie2Jie An3Nan Huang4National Key Laboratory of Science and Technology on Communication, University of Electronic Science and Technology of China, Chengdu 610000, ChinaNational Key Laboratory of Science and Technology on Communication, University of Electronic Science and Technology of China, Chengdu 610000, ChinaNational Key Laboratory of Science and Technology on Communication, University of Electronic Science and Technology of China, Chengdu 610000, ChinaNational Key Laboratory of Science and Technology on Communication, University of Electronic Science and Technology of China, Chengdu 610000, ChinaNational Key Laboratory of Science and Technology on Communication, University of Electronic Science and Technology of China, Chengdu 610000, ChinaUnderwater acoustic signal separation is a key technique for underwater communications. The existing methods are mostly model-based, and cannot accurately characterize the practical underwater acoustic communication environment. They are only suitable for binary signal separation and cannot handle multivariate signal separation. However, recurrent neural networks (RNNs) show a powerful ability to extract the features of temporal sequences. Inspired by this, in this paper, we present a data-driven approach for underwater acoustic signal separation using deep learning technology. We use a bidirectional long short-term memory (Bi-LSTM) approach to explore the features of a time–frequency (T-F) mask, and propose a T-F-mask-aware Bi-LSTM for signal separation. Taking advantage of the sparseness of the T-F image, the designed Bi-LSTM network is able to extract the discriminative features for separation, which further improves the separation performance. In particular, this method breaks through the limitations of the existing methods and not only achieves good results in multivariate separation but also effectively separates signals when they are mixed with 40 dB Gaussian noise signals. The experimental results show that this method can achieve a 97% guarantee ratio (PSR), and the average similarity coefficient of the multivariate signal separation is stable above 0.8 under high noise conditions. It should be noted that our model can only handle known signals such as test signals for calibration.https://www.mdpi.com/1424-8220/22/15/5598blind source separationbinary maskdeep learningunderwater acoustic signal |
| spellingShingle | Jie Chen Chang Liu Jiawu Xie Jie An Nan Huang Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation Sensors blind source separation binary mask deep learning underwater acoustic signal |
| title | Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation |
| title_full | Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation |
| title_fullStr | Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation |
| title_full_unstemmed | Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation |
| title_short | Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation |
| title_sort | time frequency mask aware bidirectional lstm a deep learning approach for underwater acoustic signal separation |
| topic | blind source separation binary mask deep learning underwater acoustic signal |
| url | https://www.mdpi.com/1424-8220/22/15/5598 |
| work_keys_str_mv | AT jiechen timefrequencymaskawarebidirectionallstmadeeplearningapproachforunderwateracousticsignalseparation AT changliu timefrequencymaskawarebidirectionallstmadeeplearningapproachforunderwateracousticsignalseparation AT jiawuxie timefrequencymaskawarebidirectionallstmadeeplearningapproachforunderwateracousticsignalseparation AT jiean timefrequencymaskawarebidirectionallstmadeeplearningapproachforunderwateracousticsignalseparation AT nanhuang timefrequencymaskawarebidirectionallstmadeeplearningapproachforunderwateracousticsignalseparation |