{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:16:04Z","timestamp":1776885364235,"version":"3.51.2"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Research, Samsung Electronics Company Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3381910","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T19:52:20Z","timestamp":1711569140000},"page":"979-983","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Parallel Audio Generation Using Group Masked Language Modeling"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4689-3110","authenticated-orcid":false,"given":"Myeonghun","family":"Jeong","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8150-765X","authenticated-orcid":false,"given":"Minchan","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3316-4808","authenticated-orcid":false,"given":"Joun Yeop","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Research, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"2835-8856","key":"ref1","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref4","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref5","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref6","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"key":"ref7","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref9","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref11","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023"},{"key":"ref12","article-title":"VampNet: Music generation via masked acoustic token modeling","volume-title":"Proc. Ismir 2023 Hybrid Conf.","author":"Garcia","year":"2023"},{"key":"ref13","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shen","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447392"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref17","article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref18","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref19","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref23","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Baevski","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-225"},{"key":"ref25","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref29","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref31","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10480225.pdf?arnumber=10480225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T20:02:49Z","timestamp":1712692969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10480225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3381910","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}