{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:13:52Z","timestamp":1783764832849,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819228584","type":"print"},{"value":"9789819228591","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-2859-1_6","type":"book-chapter","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:05:05Z","timestamp":1783764305000},"page":"68-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GAGE: Generative Adversarial Enhancement for\u00a0High-Fidelity Audio Watermark Removal"],"prefix":"10.1007","author":[{"given":"Wenjing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangcun","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengde","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhong","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of ICCV Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"6_CR2","unstructured":"Chen, G., Wu, Y., Liu, S., Liu, T., Du, X., Wei, F.: WavMark: watermarking for audio generation. arXiv preprint arXiv:2308.12770 (2023)"},{"issue":"1","key":"6_CR3","first-page":"56","volume":"11","author":"N Cvejic","year":"2005","unstructured":"Cvejic, N., Sepp\u00e4nen, T.: Increasing robustness of LSB audio steganography by reduced distortion LSB coding. J. Univ. Comput. Sci. 11(1), 56\u201365 (2005)","journal-title":"J. Univ. Comput. Sci."},{"key":"6_CR4","unstructured":"Defferrard, M., Benzi, K., Vandergheynst, P., Bresson, X.: FMA: a dataset for music analysis. In: Proceedings of ISMIR, pp. 316\u2013323 (2017)"},{"key":"6_CR5","unstructured":"D\u00e9fossez, A., Copet, J., Synnaeve, G., Adi, Y.: High fidelity neural audio compression. Trans. Mach. Learn. Res. 2023 (2023)"},{"issue":"1","key":"6_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-015-0054-9","volume":"2015","author":"A Hines","year":"2015","unstructured":"Hines, A., Skoglund, J., Kokaram, A.C., Harte, N.: ViSQOL: an objective speech quality model. EURASIP J. Audio Speech Music Process. 2015(1), 1\u201318 (2015). https:\/\/doi.org\/10.1186\/s13636-015-0054-9","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Hu, Y., et al.: DCCRN: deep complex convolution recurrent network for phase-aware speech enhancement. In: Proceedings of INTERSPEECH, pp. 2472\u20132476 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-2537","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Kavalerov, I., et al.: Universal sound separation. In: Proceedings of IEEE WASPAA, pp. 175\u2013179 (2019). https:\/\/doi.org\/10.1109\/WASPAA.2019.8937253","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Kumar, R., Seetharaman, P., Luebs, A., Kumar, I., Kumar, K.: High-fidelity audio compression with improved RVQGAN. In: Proceedings of NeurIPS (2023)","DOI":"10.52202\/075280-1214"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Le\u00a0Roux, J., Wisdom, S., Erdogan, H., Hershey, J.R.: SDR \u2013 half-baked or well done? In: Proceedings of IEEE ICASSP, pp. 626\u2013630 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683855","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"6_CR12","unstructured":"Lehtinen, J., et al.: Noise2Noise: learning image restoration without clean data. In: Proceedings of ICML (2018)"},{"key":"6_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111366","volume":"162","author":"G Lin","year":"2025","unstructured":"Lin, G., Luo, W., Zheng, P., Huang, J.: An audio watermarking method against re-recording distortions. Pattern Recogn. 162, 111366 (2025). https:\/\/doi.org\/10.1016\/j.patcog.2025.111366","journal-title":"Pattern Recogn."},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Liu, C., Zhang, J., Fang, H., Ma, Z., Zhang, W., Yu, N.: DeAR: a deep-learning-based audio re-recording resilient watermarking. In: Proceedings of AAAI, vol.\u00a037, pp. 13201\u201313209 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i11.26550","DOI":"10.1609\/aaai.v37i11.26550"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Liu, C., Zhang, J., Zhang, T., Yang, X., Zhang, W., Yu, N.: Detecting voice cloning attacks via timbre watermarking. In: Proceedings of NDSS (2024)","DOI":"10.14722\/ndss.2024.24200"},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Liu, H., Guo, M., Jiang, Z., Wang, L., Gong, N.Z.: AudioMarkBench: benchmarking robustness of audio watermarking. In: Proceedings of NeurIPS, vol.\u00a037 (2024). https:\/\/doi.org\/10.52202\/079017-1656, datasets and Benchmarks Track","DOI":"10.52202\/079017-1656"},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"L\u00f3pez-L\u00f3pez, A., Rosell\u00f3, V., G\u00f3mez, P.: Speech watermarking removal by DNN-based speech enhancement attacks. In: Proceedings of IberSPEECH (2024). https:\/\/doi.org\/10.21437\/IberSPEECH.2024-4","DOI":"10.21437\/IberSPEECH.2024-4"},{"issue":"11","key":"6_CR18","doi-asserted-by":"publisher","first-page":"2176","DOI":"10.1109\/TASLP.2017.2749001","volume":"25","author":"I Natgunanathan","year":"2017","unstructured":"Natgunanathan, I., Xiang, Y., Beliakov, G., Scoglio, C.: Patchwork-based multilayer audio watermarking. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(11), 2176\u20132187 (2017). https:\/\/doi.org\/10.1109\/TASLP.2017.2749001","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"6_CR19","doi-asserted-by":"publisher","unstructured":"\u00d6zer, A., et al.: RAW-Bench: benchmarking robustness of audio watermarking. In: Proceedings of INTERSPEECH, pp. 774\u2013778 (2025). https:\/\/doi.org\/10.21437\/Interspeech.2025-665","DOI":"10.21437\/Interspeech.2025-665"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Reddy, C.K.A., et al.: INTERSPEECH 2021 deep noise suppression challenge. In: Proceedings of INTERSPEECH, pp. 2796\u20132800 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-1609","DOI":"10.21437\/Interspeech.2021-1609"},{"key":"6_CR21","unstructured":"San\u00a0Roman, R., Fernandez, P., D\u00e9fossez, A., Furon, T., Tran, T., Elsahar, H.: Proactive detection of voice cloning with localized watermarking. In: Proceedings of ICML (2024)"},{"key":"6_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR (2015)"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Singh, M.K., Takahashi, N., Liao, W.H., Mitsufuji, Y.: SilentCipher: deep audio watermarking. In: Proceedings of INTERSPEECH (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-174","DOI":"10.21437\/Interspeech.2024-174"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Steinebach, M., et al.: Stirmark benchmark: audio watermarking attacks. In: International Conference on Information Technology: Coding and Computing (ITCC), pp. 49\u201354. IEEE, Las Vegas, NV, USA (2001)","DOI":"10.1109\/ITCC.2001.918764"},{"key":"6_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of NeurIPS (2017)"},{"key":"6_CR26","doi-asserted-by":"publisher","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of IEEE CVPR (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00917","DOI":"10.1109\/CVPR.2018.00917"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of IEEE CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"6_CR28","unstructured":"Wen, Y., Innuganti, A., Ramos, A.B., Guo, H., Yan, Q.: SoK: how robust is audio watermarking in generative AI models? arXiv preprint arXiv:2503.19176 (2025)"},{"key":"6_CR29","doi-asserted-by":"publisher","unstructured":"Williamson, D.S., Wang, Y., Wang, D.: Complex ratio masking for monaural speech separation. In: Proceedings of IEEE ICASSP, pp. 5220\u20135224 (2016). https:\/\/doi.org\/10.1109\/ICASSP.2016.7472673","DOI":"10.1109\/ICASSP.2016.7472673"},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of ECCV, pp. 3\u201319 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Yamagishi, J., Veaux, C., MacDonald, K.: CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92) [dataset]. University of Edinburgh, The Centre for Speech Technology Research (CSTR) (2019). https:\/\/doi.org\/10.7488\/ds\/2645","DOI":"10.7488\/ds\/2645"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"Yamamoto, R., Song, E., Kim, J.M.: Parallel WaveGAN: a fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. In: Proceedings of IEEE ICASSP, pp. 6199\u20136203 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053795","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"6_CR33","unstructured":"Zhang, R.: Making convolutional networks shift-invariant again. In: Proceedings of ICML, pp. 7324\u20137334 (2019)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2859-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:05:08Z","timestamp":1783764308000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2859-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,12]]},"ISBN":["9789819228584","9789819228591"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2859-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,12]]},"assertion":[{"value":"12 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}