{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:19:19Z","timestamp":1774419559884,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890096","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Code Drift: Towards Idempotent Neural Audio Codecs"],"prefix":"10.1109","author":[{"given":"Patrick","family":"O\u2019Reilly","sequence":"first","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prem","family":"Seetharaman","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqu","family":"Su","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Pardo","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep contextual video compression","author":"Li","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00462"},{"key":"ref3","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref5","article-title":"Simple and controllable music generation","author":"Copet","year":"2024","journal-title":"Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-590"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref8","article-title":"Vampnet: Music generation via masked acoustic token modeling","volume-title":"ISMIR","author":"Garcia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref10","article-title":"Tandem Coding","volume-title":"AES Coding Tutorial","author":"Erlangen"},{"key":"ref11","article-title":"An audio codec for multiple compression without loss of perceptual quality","volume-title":"Proceedings of the 17th International AES Conference on High Quality Audio Coding","author":"Kurth"},{"key":"ref12","article-title":"Cascading of different audio codecs","volume-title":"Proceedings of the 100th AES Convention","author":"Ritscher"},{"key":"ref13","article-title":"Idempotence and perceptual image compression","volume-title":"ICLR","author":"Xu"},{"key":"ref14","article-title":"Mp3 (mpeg layer iii audio encoding)","year":"1993"},{"key":"ref15","article-title":"Definition of the opus audio codec","volume-title":"IETF RFC 6716","author":"Valin","year":"2012"},{"key":"ref16","article-title":"High-fidelity audio compression with improved rvqgan","volume-title":"NeurIPS","author":"Kumar"},{"key":"ref17","article-title":"Speechtokenizer: Unified speech tokenizer for speech large language models","volume-title":"ICLR","author":"Zhang"},{"key":"ref18","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024"},{"key":"ref19","article-title":"Spectral codecs: Spectrogram-based audio codecs for high quality speech synthesis","author":"Langman","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.562"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129994"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448454"},{"key":"ref23","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023"},{"key":"ref24","article-title":"Audiogen: Textually guided audio generation","volume-title":"ICLR","author":"Kreuk"},{"key":"ref25","article-title":"Dasb - discrete audio and speech benchmark","author":"Mousavi","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref27","article-title":"Towards audio language modeling \u2013 an overview","author":"Wu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832364"},{"key":"ref29","article-title":"An independence-promoting loss for music generation with language models","volume-title":"ICML","author":"Lemercier"},{"key":"ref30","article-title":"Evaluating strong idempotence of image codec","author":"Zhang","year":"2023"},{"key":"ref31","article-title":"Idempotent learned image compression with right-inverse","volume-title":"NeurIPS","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413680"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1905"},{"key":"ref34","article-title":"English multi-speaker corpus for cstr voice cloning toolkit","author":"Yamagishi","year":"2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref37","article-title":"Neural discrete representation learning","volume-title":"NeurIPS","author":"van den Oord"},{"key":"ref38","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"LREC","author":"Ardila"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref40","first-page":"993","article-title":"VoxPopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Wang"},{"key":"ref41","article-title":"Chunked autoregressive gan for conditional waveform synthesis","volume-title":"ICLR","author":"Morrison"},{"key":"ref42","article-title":"Bigvgan: A universal neural vocoder with large-scale training","volume-title":"ICLR","author":"Lee"},{"key":"ref43","article-title":"The lj speech dataset","author":"Ito"},{"key":"ref44","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref45","article-title":"The curious case of neural text degeneration","volume-title":"ICLR","author":"Holtzman"},{"key":"ref46","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref48","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref49","article-title":"Token telephone","author":"Garcia","year":"2024","journal-title":"New Interfaces for Musical Expression (NIME)"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890096.pdf?arnumber=10890096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:30Z","timestamp":1774416210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890096","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}