{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T22:28:27Z","timestamp":1783204107941,"version":"3.54.6"},"reference-count":35,"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\/icassp48485.2024.10447253","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4650-4654","source":"Crossref","is-referenced-by-count":12,"title":["Maskmark: Robust Neuralwatermarking for Real and Synthetic Speech"],"prefix":"10.1109","author":[{"given":"Patrick","family":"O\u2019Reilly","sequence":"first","affiliation":[{"name":"Northwestern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Su","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan","family":"Pardo","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Polish startup wows with \u2018deep fake\u2019 voice cloning tool which can make leonardo dicaprio sound like kim kardashian","author":"Dowell","year":"2023","journal-title":"TheFirstNews"},{"key":"ref2","article-title":"A new ai voice tool is already being abused to make deepfake celebrity audio clips","author":"Moon","year":"2023","journal-title":"Engadget"},{"key":"ref3","article-title":"An a.i. hit of fake \u2018drake\u2019 and \u2018the weeknd\u2019 rattles the music world","author":"Coscarelli","year":"2023","journal-title":"The New York Times"},{"key":"ref4","article-title":"People are trying to claim real videos are deepfakes. the courts are not amused","author":"Bond","year":"2023","journal-title":"National Public Radio"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233236"},{"key":"ref7","article-title":"Bigvgan: A universal neural vocoder with large-scale training","author":"Lee","year":"2023","journal-title":"ICLR"},{"key":"ref8","article-title":"Chunked autoregressive gan for conditional waveform synthesis","author":"Morrison","year":"2022","journal-title":"ICLR"},{"key":"ref9","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"Kim","year":"2021","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3356232\/mm1"},{"key":"ref11","article-title":"Introducing the watermark algorithm for synthetic voice identification","author":"Cui","year":"2022","journal-title":"Azure AI services Blog"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26550"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103381"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2003.809384"},{"key":"ref17","article-title":"English multi-speaker corpus for cstr voice cloning toolkit","author":"Yamagishi","year":"2012"},{"key":"ref18","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1612524113"},{"key":"ref22","article-title":"Voiceblock: Privacy through real-time adversarial attacks with audio-to-audio models","author":"O\u2019Reilly","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref24","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231926"},{"key":"ref26","first-page":"2013","article-title":"Incorporating nesterov momentum into adam","volume-title":"ICLR Workshop","author":"Dozat"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2379648"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref29","article-title":"Treering watermarks: Fingerprints for diffusion images that are invisible and robust","author":"Wen","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0025"},{"key":"ref31","article-title":"Vocos: Closing the gap between time-domain and fourier-based neural vocoders for high-quality audio synthesis","author":"Siuzdak","year":"2023"},{"key":"ref32","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2021","journal-title":"ICLR"},{"key":"ref33","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref34","article-title":"High-fidelity audio compression with improved rvqgan","author":"Kumar","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10447253.pdf?arnumber=10447253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:42:39Z","timestamp":1722573759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447253","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}