{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:38Z","timestamp":1777657478816,"version":"3.51.4"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726484","type":"print"},{"value":"9783031726491","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72649-1_19","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"331-349","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Mutual Learning for\u00a0Acoustic Matching and\u00a0Dereverberation via\u00a0Visual Scene-Driven Diffusion"],"prefix":"10.1007","author":[{"given":"Jian","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"issue":"7","key":"19_CR2","doi-asserted-by":"publisher","first-page":"1524","DOI":"10.1109\/TASL.2013.2256897","volume":"21","author":"S Bilbao","year":"2013","unstructured":"Bilbao, S.: Modeling of complex geometries and boundary conditions in finite difference\/finite volume time domain room acoustics simulation. IEEE Trans. Audio Speech Lang. Process. 21(7), 1524\u20131533 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"6","key":"19_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2980179.2982431","volume":"35","author":"C Cao","year":"2016","unstructured":"Cao, C., Ren, Z., Schissler, C., Manocha, D., Zhou, K.: Interactive sound propagation with bidirectional path tracing. ACM Trans. Graph. 35(6), 1\u201311 (2016)","journal-title":"ACM Trans. Graph."},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Gao, R., Calamia, P., Grauman, K.: Visual acoustic matching. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., et al.: Soundspaces: audio-visual navigation in 3d environments. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C., Sun, W., Harwath, D., Grauman, K.: Learning audio-visual dereverberation. In: ICASSP (2023)","DOI":"10.1109\/ICASSP49357.2023.10095818"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, W., Liu, S., Li, H., Yang, Y.: Omnidirectional information gathering for knowledge transfer-based audio-visual navigation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01009"},{"key":"19_CR8","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: NeurIPS (2016)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., Yoon, S.: ILVR: conditioning method for denoising diffusion probabilistic models. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"19_CR10","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. In: SIGGRAPH (2018)","DOI":"10.1145\/3197517.3201357"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Ernst, O., Chazan, S.E., Gannot, S., Goldberger, J.: Speech dereverberation using fully convolutional networks. In: EUSIPCO (2018)","DOI":"10.23919\/EUSIPCO.2018.8553141"},{"key":"19_CR13","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: NeurIPS (2018)"},{"key":"19_CR14","unstructured":"Fu, S.W., Liao, C.F., Tsao, Y., Lin, S.D.: Metricgan: generative adversarial networks based black-box metric scores optimization for speech enhancement. In: ICML (2019)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Fu, S., et al.: Metricgan+: an improved version of metricgan for speech enhancement. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-599"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Funkhouser, T., et al.: A beam tracing method for interactive architectural acoustics. The Journal of the acoustical society of America 115(2), 739\u2013756 (2004)","DOI":"10.1121\/1.1641020"},{"key":"19_CR17","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/978-1-4939-0755-7_9","volume-title":"Springer Handbook of Acoustics","author":"AC Gade","year":"2014","unstructured":"Gade, A.C.: Acoustics in halls for speech and music. In: Rossing, T.D. (ed.) Springer Handbook of Acoustics, pp. 317\u2013366. Springer, New York (2014). https:\/\/doi.org\/10.1007\/978-1-4939-0755-7_9"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Gamper, H., Tashev, I.J.: Blind reverberation time estimation using a convolutional neural network. In: IWAENC (2018)","DOI":"10.1109\/IWAENC.2018.8521241"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: 2.5d visual sound. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00041"},{"key":"19_CR20","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"issue":"6","key":"19_CR21","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/TASLP.2015.2416653","volume":"23","author":"K Han","year":"2015","unstructured":"Han, K., Wang, Y., Wang, D., Woods, W.S., Merks, I., Zhang, T.: Learning spectral mapping for speech dereverberation and denoising. IEEE Trans. Audio Speech Lang. Process. 23(6), 982\u2013992 (2015)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"6","key":"19_CR22","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/TASLP.2015.2416653","volume":"23","author":"K Han","year":"2015","unstructured":"Han, K., Wang, Y., Wang, D., Woods, W.S., Merks, I., Zhang, T.: Learning spectral mapping for speech dereverberation and denoising. IEEE Trans. Audio Speech Lang. Process. 23(6), 982\u2013992 (2015)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"19_CR23","unstructured":"He, D., et al.: Dual learning for machine translation. In: NeurIPS (2016)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR25","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A.: Unit: multimodal multitask learning with a unified transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"19_CR27","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Ke, L., et al.: Tactical rewind: self-correction via backtracking in vision-and-language navigation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00690"},{"key":"19_CR30","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS (2020)"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Kim, J., Gopakumar, M., Choi, S., Peng, Y., Lopes, W., Wetzstein, G.: Holographic glasses for virtual reality. In: SIGGRAPH (2022)","DOI":"10.1145\/3528233.3530739"},{"key":"19_CR32","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Seltzer, M.L., Khudanpur, S.: A study on data augmentation of reverberant speech for robust speech recognition. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Kon, H., Koike, H.: Estimation of late reverberation characteristics from a single two-dimensional environmental image using convolutional neural networks. J. Audio Eng. Soc. 67(7\/8), 540\u2013548 (2019)","DOI":"10.17743\/jaes.2018.0069"},{"key":"19_CR35","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: Diffwave: a versatile diffusion model for audio synthesis. In: ICLR (2021)"},{"issue":"2","key":"19_CR36","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1121\/1.5051640","volume":"144","author":"AA Kressner","year":"2018","unstructured":"Kressner, A.A., Westermann, A., Buchholz, J.M.: The impact of reverberation on speech intelligibility in cochlear implant recipients. J. Acoust. Soc. Am. 144(2), 1113\u20131122 (2018)","journal-title":"J. Acoust. Soc. Am."},{"key":"19_CR37","doi-asserted-by":"publisher","unstructured":"Kuttruff, H., Mommertz, E.: Room acoustics. In: M\u00fcller, G., M\u00f6ser, M. (eds.) Handbook of Engineering Acoustics, pp. 239\u2013267. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-540-69460-1_10","DOI":"10.1007\/978-3-540-69460-1_10"},{"key":"19_CR38","unstructured":"Larsen, A.B.L., S\u00f8nderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. In: ICML (2016)"},{"key":"19_CR39","unstructured":"Lee, S., Ping, W., Ginsburg, B., Catanzaro, B., Yoon, S.: Bigvgan: a universal neural vocoder with large-scale training. In: ICLR (2023)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Li, K., Yang, Z., Chen, L., Yang, Y., Xiao, J.: CATR: combinatorial-dependence audio-queried transformer for audio-visual video segmentation. In: ACM MM (2023)","DOI":"10.1145\/3581783.3611724"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: More control for free! image synthesis with semantic diffusion guidance. In: WACV (2023)","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"19_CR42","unstructured":"Lu, J., Kannan, A., Yang, J., Parikh, D., Batra, D.: Best of both worlds: transferring knowledge from discriminative learning to a generative visual dialog model. In: NeurIPS (2017)"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Gool, L.V.: Repaint: inpainting using denoising diffusion probabilistic models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Ma, J., Wang, W., Yang, Y., Zheng, F.: Ms2sl: multimodal spoken data-driven continuous sign language production. In: ACL (2024)","DOI":"10.18653\/v1\/2024.findings-acl.432"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Mack, W., Deng, S., Habets, E.A.P.: Single-channel blind direct-to-reverberation ratio estimation using masking. In: Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-2171"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Malpica, S., et al.: Auditory stimuli degrade visual performance in virtual reality. In: SIGGRAPH (2022)","DOI":"10.1145\/3532719.3543220"},{"key":"19_CR47","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"19_CR48","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"19_CR49","unstructured":"Mittal, G., Engel, J.H., Hawthorne, C., Simon, I.: Symbolic music generation with diffusion models. In: ISMIR (2021)"},{"issue":"2","key":"19_CR50","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/29.1509","volume":"36","author":"M Miyoshi","year":"1988","unstructured":"Miyoshi, M., Kaneda, Y.: Inverse filtering of room acoustics. IEEE Trans. Audio Speech Lang. Process. 36(2), 145\u2013152 (1988)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"19_CR51","unstructured":"Murgai, P., Rau, M., Jot, J.M.: Blind estimation of the reverberation fingerprint of unknown acoustic environments. In: Audio Engineering Society Convention, vol. 143. Audio Engineering Society (2017)"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Nakatani, T., B\u00f6ddeker, C., Kinoshita, K., Ikeshita, R., Delcroix, M., Haeb-Umbach, R.: Jointly optimal denoising, dereverberation, and source separation. IEEE Trans. Audio Speech Lang. Process. 28, 2267\u20132282 (2020)","DOI":"10.1109\/TASLP.2020.3013118"},{"issue":"7","key":"19_CR53","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1109\/TASL.2010.2052251","volume":"18","author":"T Nakatani","year":"2010","unstructured":"Nakatani, T., Yoshioka, T., Kinoshita, K., Miyoshi, M., Juang, B.H.: Speech dereverberation based on variance-normalized delayed linear prediction. IEEE Trans. Audio Speech Lang. Process. 18(7), 1717\u20131731 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Naylor, P.A., Gaubitch, N.D., et\u00a0al.: Speech Dereverberation, vol.\u00a02. Springer (2010)","DOI":"10.1007\/978-1-84996-056-4"},{"key":"19_CR55","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML (2021)"},{"key":"19_CR56","unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"19_CR57","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: ICASSP (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"19_CR58","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"19_CR59","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2016)"},{"issue":"5","key":"19_CR60","doi-asserted-by":"publisher","first-page":"2999","DOI":"10.1121\/1.3641368","volume":"130","author":"J Rennies","year":"2011","unstructured":"Rennies, J., Brand, T., Kollmeier, B.: Prediction of the influence of reverberation on binaural speech intelligibility in noise and in quiet. J. Acoust. Soc. Am. 130(5), 2999\u20133012 (2011)","journal-title":"J. Acoust. Soc. Am."},{"key":"19_CR61","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., Hekstra, A.P.: Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: ICASSP (2001)"},{"key":"19_CR62","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)","DOI":"10.1145\/3528233.3530757"},{"issue":"4","key":"19_CR63","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1121\/AT.2020.16.4.48","volume":"16","author":"L Savioja","year":"2020","unstructured":"Savioja, L., Xiang, N.: Simulation-based auralization of room acoustics. Acoust. Today 16(4), 48\u201355 (2020)","journal-title":"Acoust. Today"},{"key":"19_CR64","doi-asserted-by":"crossref","unstructured":"Schroeder, M.R., Logan, B.F.: \u201cColorless\u201d artificial reverberation. IRE Trans. Audio (6), 209\u2013214 (1961)","DOI":"10.1109\/TAU.1961.1166351"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"Shah, M., Chen, X., Rohrbach, M., Parikh, D.: Cycle-consistency for robust visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00681"},{"key":"19_CR66","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: FLAVA: a foundational language and vision alignment model. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"19_CR67","doi-asserted-by":"crossref","unstructured":"Singh, N., Mentch, J., Ng, J., Beveridge, M., Drori, I.: Image2reverb: cross-modal reverb impulse response synthesis. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00035"},{"key":"19_CR68","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"19_CR69","doi-asserted-by":"crossref","unstructured":"Su, J., Jin, Z., Finkelstein, A.: Acoustic matching by embedding impulse responses. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9054701"},{"key":"19_CR70","doi-asserted-by":"crossref","unstructured":"Sunkara, R., Luo, T.: No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects. In: ECML (2022)","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"19_CR71","doi-asserted-by":"crossref","unstructured":"Tan, H., Yu, L., Bansal, M.: Learning to navigate unseen environments: back translation with environmental dropout. In: NAACL (2019)","DOI":"10.18653\/v1\/N19-1268"},{"issue":"3","key":"19_CR72","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1109\/JSTSP.2020.2987209","volume":"14","author":"K Tan","year":"2020","unstructured":"Tan, K., Xu, Y., Zhang, S., Yu, M., Yu, D.: Audio-visual speech separation and dereverberation with a two-stage multimodal network. IEEE J. Sel. Top. Signal Process. 14(3), 542\u2013553 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"19_CR73","doi-asserted-by":"crossref","unstructured":"V\u00e4lim\u00e4ki, V., Parker, J.D., Savioja, L., III, J.O.S., Abel, J.S.: Fifty years of artificial reverberation. IEEE Trans. Speech Audio Process. 20(5), 1421\u20131448 (2012)","DOI":"10.1109\/TASL.2012.2189567"},{"key":"19_CR74","doi-asserted-by":"crossref","unstructured":"Wang, H., Liang, W., Shen, J., Gool, L.V., Wang, W.: Counterfactual cycle-consistent learning for instruction following and generation in vision-language navigation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"19_CR75","unstructured":"Wang, P., et al.: OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: ICML (2022)"},{"key":"19_CR76","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, W., Liang, W., Yu, L.: Comic-guided speech synthesis. ACM Trans. Graph. 38(6), 187:1\u2013187:14 (2019)","DOI":"10.1145\/3355089.3356487"},{"key":"19_CR77","doi-asserted-by":"crossref","unstructured":"Wu, B., et al.: An end-to-end deep learning approach to simultaneous speech dereverberation and acoustic modeling for robust speech recognition. IEEE J. Select. Topics Signal Process. 11(8), 1289\u20131300 (2017)","DOI":"10.1109\/JSTSP.2017.2756439"},{"issue":"1","key":"19_CR78","first-page":"98","volume":"25","author":"B Wu","year":"2017","unstructured":"Wu, B., Li, K., Yang, M., Lee, C.: A reverberation-time-aware approach to speech dereverberation based on deep neural networks. IEEE Trans. Audio Speech Lang. Process. 25(1), 98\u2013107 (2017)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"19_CR79","unstructured":"Xie, Q., Dai, Z., Hovy, E.H., Luong, T., Le, Q.: Unsupervised data augmentation for consistency training. In: NeurIPS (2020)"},{"key":"19_CR80","unstructured":"Yang, Z., Chen, G., Li, X., Wang, W., Yang, Y.: Doraemongpt: toward understanding dynamic scenes with large language models. In: ICML (2024)"},{"key":"19_CR81","doi-asserted-by":"crossref","unstructured":"Yi, Z., Zhang, H.R., Tan, P., Gong, M.: Dualgan: unsupervised dual learning for image-to-image translation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.310"},{"key":"19_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"19_CR83","doi-asserted-by":"publisher","first-page":"1598","DOI":"10.1109\/TASLP.2020.2995273","volume":"28","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Wang, D., Xu, B., Zhang, T.: Monaural speech dereverberation using temporal convolutional networks with self attention. IEEE Trans. Audio Speech Lang. Process. 28, 1598\u20131607 (2020)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"19_CR84","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/TASLP.2018.2870725","volume":"27","author":"Y Zhao","year":"2019","unstructured":"Zhao, Y., Wang, Z., Wang, D.: Two-stage deep learning for noisy-reverberant speech enhancement. IEEE Trans. Audio Speech Lang. Process. 27(1), 53\u201362 (2019)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"19_CR85","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Xia, Y., Qin, T., Xia, L., Liu, T.: Dual learning: theoretical study and an algorithmic extension. In: ACML (2020)","DOI":"10.1007\/s42979-021-00799-y"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72649-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:11:50Z","timestamp":1727593910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72649-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726484","9783031726491"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72649-1_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}