{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T15:46:38Z","timestamp":1746287198806,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448134","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11231-11235","source":"Crossref","is-referenced-by-count":4,"title":["Collaborative Watermarking for Adversarial Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Lauri","family":"Juvela","sequence":"first","affiliation":[{"name":"Aalto University,Espoo,Finland"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"Jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1281"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952516"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref10","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1965"},{"key":"ref13","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/79.879339"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1996.560429"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1147\/sj.353.0313"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61996-8_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103381"},{"journal-title":"Wav-mark: Watermarking for audio generation","year":"2023","author":"Chen","key":"ref19"},{"volume-title":"Digitale Wasserzeichen fuer Audiodaten","year":"2004","author":"Steinebach","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01418"},{"article-title":"Responsible disclosure of generative models using scalable fingerprinting","volume-title":"Proc. ICLR","author":"Yu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094779"},{"key":"ref24","first-page":"23433","article-title":"Removing batch normalization boosts adversarial training","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414234"},{"article-title":"MUSAN: A Music, Speech, and Noise Corpus","year":"2015","author":"Snyder","key":"ref29"},{"article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref30"},{"article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. ICLR","author":"Chen","key":"ref31"},{"article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong","key":"ref32"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448134.pdf?arnumber=10448134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:36:00Z","timestamp":1722573360000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448134\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448134","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}