{"title":"利用注意力深度神经网络检测频谱图中的频率线","authors":"DingLin Jiang, Xinwei Luo, Qifan Shen","doi":"10.1121/10.0034360","DOIUrl":null,"url":null,"abstract":"<p><p>In this paper, a frequency line detection network (FLDNet) is proposed to effectively detect multiple weak frequency lines and time-varying frequency lines in underwater acoustic signals under low signal-to-noise ratios (SNRs). FLDNet adopts an encoder-decoder architecture as the basic framework, where the encoder is designed to obtain multilevel features of the frequency lines, and the decoder is responsible for reconstructing the frequency lines. FLDNet includes attention-based feature fusion modules that combine deep semantic features with shallow features learned by the encoder to reduce noise in the decoder's deep feature representation and improve reconstruction accuracy. In addition, a composite loss function was constructed by using the continuity of frequency lines, which improved the detection performance of frequency lines. After training through simulated signal sets, FLDNet can effectively detect frequency lines in spectrograms of simulated and measured signals. The experimental results indicate that FLDNet is superior to other state-of-the-art methods, even at SNRs as low as -28 dB.</p>","PeriodicalId":17168,"journal":{"name":"Journal of the Acoustical Society of America","volume":"156 5","pages":"3204-3216"},"PeriodicalIF":2.1000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Frequency line detection in spectrograms using a deep neural network with attention.\",\"authors\":\"DingLin Jiang, Xinwei Luo, Qifan Shen\",\"doi\":\"10.1121/10.0034360\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In this paper, a frequency line detection network (FLDNet) is proposed to effectively detect multiple weak frequency lines and time-varying frequency lines in underwater acoustic signals under low signal-to-noise ratios (SNRs). FLDNet adopts an encoder-decoder architecture as the basic framework, where the encoder is designed to obtain multilevel features of the frequency lines, and the decoder is responsible for reconstructing the frequency lines. FLDNet includes attention-based feature fusion modules that combine deep semantic features with shallow features learned by the encoder to reduce noise in the decoder's deep feature representation and improve reconstruction accuracy. In addition, a composite loss function was constructed by using the continuity of frequency lines, which improved the detection performance of frequency lines. After training through simulated signal sets, FLDNet can effectively detect frequency lines in spectrograms of simulated and measured signals. The experimental results indicate that FLDNet is superior to other state-of-the-art methods, even at SNRs as low as -28 dB.</p>\",\"PeriodicalId\":17168,\"journal\":{\"name\":\"Journal of the Acoustical Society of America\",\"volume\":\"156 5\",\"pages\":\"3204-3216\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of the Acoustical Society of America\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1121/10.0034360\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ACOUSTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Acoustical Society of America","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1121/10.0034360","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ACOUSTICS","Score":null,"Total":0}
Frequency line detection in spectrograms using a deep neural network with attention.
In this paper, a frequency line detection network (FLDNet) is proposed to effectively detect multiple weak frequency lines and time-varying frequency lines in underwater acoustic signals under low signal-to-noise ratios (SNRs). FLDNet adopts an encoder-decoder architecture as the basic framework, where the encoder is designed to obtain multilevel features of the frequency lines, and the decoder is responsible for reconstructing the frequency lines. FLDNet includes attention-based feature fusion modules that combine deep semantic features with shallow features learned by the encoder to reduce noise in the decoder's deep feature representation and improve reconstruction accuracy. In addition, a composite loss function was constructed by using the continuity of frequency lines, which improved the detection performance of frequency lines. After training through simulated signal sets, FLDNet can effectively detect frequency lines in spectrograms of simulated and measured signals. The experimental results indicate that FLDNet is superior to other state-of-the-art methods, even at SNRs as low as -28 dB.
期刊介绍:
Since 1929 The Journal of the Acoustical Society of America has been the leading source of theoretical and experimental research results in the broad interdisciplinary study of sound. Subject coverage includes: linear and nonlinear acoustics; aeroacoustics, underwater sound and acoustical oceanography; ultrasonics and quantum acoustics; architectural and structural acoustics and vibration; speech, music and noise; psychology and physiology of hearing; engineering acoustics, transduction; bioacoustics, animal bioacoustics.