Page 162 - 《应用声学》2023年第4期
P. 162

824                                                                                  2023 年 7 月


                 tion[C]//International Conference on Medical Image  172–180, 205.
                 Computing and Computer-Assisted Intervention, 2015.  [30] 侯向丹, 赵一浩, 刘洪普, 等. 融合残差注意力机制的 UNet 视
             [23] Narayanaswamy V S, Katoch S, Thiagarajan J J, et al.  盘分割 [J]. 中国图象图形学报, 2020, 25(9): 201–215.
                 Audio source separation via multi-scale learning with di-  Hou Xiangdan, Zhao Yihao, Liu Hongpu, et al. Optic
                 lated dense U-Nets[J]. arXiv Preprint, arXiv: 1904.04161,  disk segmentation by combining UNet and residual atten-
                 2019.                                             tion mechanism[J]. Journal of Image and Graphics, 2020,
             [24] Shi Z, Lin H, Liu L, et al. Furcanext: end-to-end monau-  25(9): 201–215.
                 ral speech separation with dynamic gated dilated tem-
                                                                [31] 邢益搏, 张雄伟, 郑昌艳, 等. 骨导语音库的建立与骨气导语
                 poral convolutional networks[J]. arXiv Preprint, arXiv:
                                                                   音的互信息分析 [J]. 声学技术, 2019, 38(3): 312–316.
                 1902.04891, 2019.
                                                                   Xing Yibo, Zhang Xiongwei, Zheng Changyan, et al. Es-
             [25] Grzywalski T, Drgas S. Using recurrences in time and
                                                                   tablishment of bone-conducted speech database and mu-
                 frequency within U-net architecture for speech enhance-
                                                                   tual information analysis between bone and air-conducted
                 ment[C]//ICASSP 2019–2019 IEEE International Con-
                                                                   speeches[J]. Technical Acoustics, 2019, 38(3): 312–316.
                 ference on Acoustics, Speech and Signal Processing
                                                                [32] Rix A W, Beerends J G, Hollier M P, et al.  Per-
                 (ICASSP), 2019.
                                                                   ceptual evaluation of speech quality (PESQ): a new
             [26] Wu K, Luo J, Zeng Q, et al. Improvement in signal-to-
                                                                   method for speech quality assessment of telephone net-
                 noise ratio of liquid-state NMR spectroscopy via a deep
                                                                   works and codecs[C]//Acoustics, Speech, and Signal Pro-
                 neural network DN-UNet[J]. Analytical Chemistry, 2020,
                                                                   cessing, 2001 Proceedings (ICASSP ’01) 2001 IEEE Inter-
                 93(3): 1377–1382.
                                                                   national Conference on, 2001.
             [27] Ablavatski A, Lu S, Cai J. Enriched deep recur-
                                                                [33] Taal C H, Hendriks R C, Heusdens R, et al. A short-
                 rent visual attention model for multiple object recogni-
                                                                   time objective intelligibility measure for time-frequency
                 tion[C]//Applications of Computer Vision, 2017.
             [28] Paliwal K K, Wojcicki K, Shannon B J. The importance of  weighted noisy speech[C]//2010 IEEE International Con-
                                                                   ference on Acoustics, Speech and Signal Processing, 2010.
                 phase in speech enhancement[J]. Speech Communication,
                 2011, 53(4): 465–494.                          [34] Gray A, Markel J. Distance measures for speech process-
             [29] 董月, 冯华君, 徐之海, 等. Attention Res-Unet: 一种高         ing[J]. IEEE Transactions on Acoustics, Speech, and Sig-
                 效阴影检测算法 [J]. 浙江大学学报 (工学版), 2019, 53(2):           nal Processing, 1976, 24(5): 380–391.
                 172–180, 205.                                  [35] Tan K, Wang D L. A convolutional recurrent neural net-
                 Dong Yue, Feng Huajun, Xu Zhihai, et al. Attention Res-  work for real-time speech enhancement[C]//Interspeech
                 Unet: an efficient shadow detection algorithm[J]. Journal  2018, Hyderabad, India, 2018.
                 of Zhejiang University(Engineering Science), 2019, 53(2):
   157   158   159   160   161   162   163   164   165   166   167