{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:31:26Z","timestamp":1753601486966,"version":"3.28.0"},"reference-count":29,"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\/icassp48485.2024.10448121","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10691-10695","source":"Crossref","is-referenced-by-count":2,"title":["Mapache: Masked Parallel Transformer for Advanced Speech Editing and Synthesis"],"prefix":"10.1109","author":[{"given":"Guillermo","family":"C\u00e1mbara","sequence":"first","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick Lumban","family":"Tobing","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikolaj","family":"Babianski","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravichander","family":"Vipperla","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duo","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron","family":"Shmelkin","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Coccia","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Orazio","family":"Angelini","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnaud","family":"Joly","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mateusz","family":"Lajszczak","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Pollet","sequence":"additional","affiliation":[{"name":"Amazon Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"8","key":"ref1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"1","key":"ref2","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text Transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref3","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref4","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"journal-title":"Better speech synthesis through scaling","year":"2023","author":"Betker","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"journal-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","year":"2023","author":"Shen","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"journal-title":"High fidelity neural audio compression","year":"2022","author":"D\u00e9fossez","key":"ref10"},{"journal-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref11"},{"journal-title":"SoundStorm: Efficient parallel audio generation","year":"2023","author":"Borsos","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419418"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"journal-title":"Flow matching for generative modeling","year":"2022","author":"Lipman","key":"ref15"},{"journal-title":"Neural discrete representation learning","year":"2018","author":"van den Oord","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"journal-title":"Muse: Text-to-image generation via masked generative Transformers","year":"2023","author":"Chang","key":"ref18"},{"journal-title":"GLU variants improve Transformer","year":"2020","author":"Shazeer","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"journal-title":"Scalable diffusion models with Transformers","year":"2022","author":"Peebles","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1108\/RR-08-2013-0197"},{"key":"ref24","article-title":"The peoples speech: A large-scale diverse english speech recognition dataset for commercial usage","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Galvez","year":"2021"},{"key":"ref25","first-page":"4218","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref27","first-page":"6532","article-title":"Open-source Multi-speaker Corpora of the English Accents in the British Isles","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference (LREC)","author":"Demirsahin"},{"key":"ref28","first-page":"1399","article-title":"A3T: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"International Conference on Machine Learning","author":"Bai","year":"2022"},{"key":"ref29","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","year":"2022"}],"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\/10448121.pdf?arnumber=10448121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:39:53Z","timestamp":1731008393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448121","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}