{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T08:03:01Z","timestamp":1784361781568,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819230174","type":"print"},{"value":"9789819230181","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-92-3018-1_12","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T07:26:25Z","timestamp":1784359585000},"page":"264-284","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MelShield: Robust Mel-Domain Audio Watermarking for\u00a0Provenance Attribution of\u00a0AI Generated Synthesized Speech"],"prefix":"10.1007","author":[{"given":"Yutong","family":"Jin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingshuang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"12_CR1","unstructured":"Chen, G., Wu, Y., Liu, S., Liu, T., Du, X., Wei, F.: Wavmark: watermarking for audio generation. arXiv preprint arXiv:2308.12770 (2023)"},{"key":"12_CR2","unstructured":"Ito, K., Johnson, L.: The lj speech dataset (2017). https:\/\/keithito.com\/LJ-Speech-Dataset\/"},{"key":"12_CR3","unstructured":"Jia, Y., Zhang, Y., Weiss, R., Wang, Q.: Transfer learning from speaker verification to multispeaker text-to-speech synthesis. In: Proceedings of of NeurIPS, p. 31 (2018)"},{"key":"12_CR4","unstructured":"Kim, J., Kim, S., Kong, J., Yoon, S.: Glow-tts: a generative flow for text-to-speech via monotonic alignment search. In: Proceedings of NeurIPS (2020)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Klein, N., Chen, T., Tak, H., Casal, R., Khoury, E.: Source tracing of audio deepfake systems. arXiv preprint arXiv:2407.08016 (2024)","DOI":"10.21437\/Interspeech.2024-1283"},{"key":"12_CR6","first-page":"17022","volume":"33","author":"J Kong","year":"2020","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. Proc. NeurIPS 33, 17022\u201317033 (2020)","journal-title":"Proc. NeurIPS"},{"key":"12_CR7","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: Diffwave: a versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 (2020)"},{"key":"12_CR8","unstructured":"Lee, S.G., Ping, W., Ginsburg, B., Catanzaro, B., Yoon, S.: Bigvgan: a universal neural vocoder with large-scale training. In: Proceedings of International Conference on Learning Representations (2023)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Li, Q., Lin, X.: Proactive audio authentication using speaker identity watermarking. In: PST, pp. 1\u201310 (2024)","DOI":"10.1109\/PST62714.2024.10788060"},{"key":"12_CR10","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: Network and Distributed System Security Symposium (2024)","DOI":"10.14722\/ndss.2024.24200"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Liu, W., Li, Y., Lin, D., Tian, H., Li, H.: Groot: generating robust watermark for diffusion-model-based audio synthesis. In: Proceedings of ACM MM (2024)","DOI":"10.1145\/3664647.3680596"},{"key":"12_CR12","unstructured":"Liu, Y., Lu, L., Jin, J., Sun, L., Fanelli, A.: Xattnmark: learning robust audio watermarking with cross-attention (2025). https:\/\/arxiv.org\/abs\/2502.04230"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Reddy, C.K.A., Gopal, V., Cutler, R.: Dnsmos: a non-intrusive perceptual objective speech quality metric to evaluate noise suppressors. In: Proceedings of ICASSP, pp. 6493\u20136497 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"12_CR14","unstructured":"Ren, Y., et al.: Fastspeech 2: fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558 (2020)"},{"key":"12_CR15","doi-asserted-by":"crossref","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: Proceedings of ICASSP, vol. 2, pp. 749\u2013752 (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"12_CR16","unstructured":"Roman, R.S., Fernandez, P., D\u00e9fossez, A., Furon, T., Tran, T., Elsahar, H.: Proactive detection of voice cloning with localized watermarking. arXiv preprint arXiv:2401.17264 (2024)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions. In: Proceedings of ICASSP, pp. 4779\u20134783 (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"issue":"3","key":"12_CR18","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1121\/1.1915893","volume":"8","author":"SS Stevens","year":"1937","unstructured":"Stevens, S.S., Volkmann, J., Newman, E.B.: A scale for the measurement of the psychological magnitude pitch. J. Acoust. Soc. Am. 8(3), 185\u2013190 (1937)","journal-title":"J. Acoust. Soc. Am."},{"issue":"7","key":"12_CR19","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"Taal, C.H., Hendriks, R.C., Heusdens, R., Jensen, J.: An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19(7), 2125\u20132136 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"12_CR20","unstructured":"Van Den Oord, A., et al.: Wavenet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 12 (2016)"},{"key":"12_CR21","doi-asserted-by":"publisher","unstructured":"Wang, C., et al.: Neural codec language models are zero-shot text to speech synthesizers (2023). https:\/\/doi.org\/10.48550\/arXiv.2301.02111","DOI":"10.48550\/arXiv.2301.02111"},{"key":"12_CR22","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":"12_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: Traceablespeech: towards proactively traceable text-to-speech with watermarking (2024). https:\/\/arxiv.org\/abs\/2406.04840","DOI":"10.21437\/Interspeech.2024-534"}],"container-title":["Lecture Notes in Computer Science","Information Security and Privacy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3018-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T07:26:29Z","timestamp":1784359589000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3018-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819230174","9789819230181"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3018-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"18 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACISP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Conference on Information Security and Privacy","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"6 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acisp2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/acisp-conference.github.io\/acisp2026\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}