{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:15:47Z","timestamp":1776888947116,"version":"3.51.2"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"British Broadcasting Corporation Research and Development"},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T019751\/1"],"award-info":[{"award-number":["EP\/T019751\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ph.D. Scholarship from the Centre for Vision, Speech and Signal Processing"},{"name":"Faculty of Engineering and Physical Science"},{"DOI":"10.13039\/501100004353","name":"University of Surrey","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004353","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/jstsp.2024.3506286","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:49:07Z","timestamp":1732646947000},"page":"1448-1461","source":"Crossref","is-referenced-by-count":28,"title":["SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1036-7888","authenticated-orcid":false,"given":"Haohe","family":"Liu","sequence":"first","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guilford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8718-1278","authenticated-orcid":false,"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6887-0956","authenticated-orcid":false,"given":"Yi","family":"Yuan","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guilford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5599-8707","authenticated-orcid":false,"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guilford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9708-1075","authenticated-orcid":false,"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guilford, U.K."}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Principles of Digital Audio","author":"Pohlmann","year":"2000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv1131dh6"},{"key":"ref3","article-title":"Definition of the opus audio codec","volume-title":"Internet Eng. Task Force Standard","author":"Valin","year":"2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref5","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Den","year":"2017"},{"key":"ref6","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref7","first-page":"27980","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kumar","year":"2024"},{"key":"ref8","article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3578707"},{"key":"ref11","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref12","article-title":"AudioGen: Textually guided audio generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kreuk","year":"2022"},{"key":"ref13","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref14","first-page":"47704","article-title":"Simple and controllable music generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Copet","year":"2023"},{"key":"ref15","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref16","article-title":"Listen, think, and understand","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong","year":"2023"},{"key":"ref17","article-title":"AudioPaLM: A. large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.62"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.05.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.04.001"},{"key":"ref21","article-title":"Byte pair encoding: A text compression scheme that accelerates pattern matching","author":"Shibata","year":"1999"},{"key":"ref22","first-page":"125","article-title":"HEAR: Holistic evaluation of audio representations","volume-title":"Proc. NeurIPS Competitions Demonstrations Track","author":"Turian","year":"2022"},{"key":"ref23","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang","year":"2022"},{"issue":"14","key":"ref24","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. Berkeley Symp. Math. Statist. Probability","volume":"1","author":"MacQueen","year":"1967"},{"key":"ref25","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref26","article-title":"High-quality, low-delay music coding in the opus codec","volume-title":"Audio Eng. Soc. Conv.","author":"Valin","year":"2013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref32","first-page":"5178","article-title":"Beats: Audio pre-training with acoustic tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref34","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref35","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn. Res.","author":"Rezende","year":"2015"},{"key":"ref36","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov","year":"2021"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref39","first-page":"23689","article-title":"BinauralGrad: A two-stage conditional diffusion probabilistic model for binaural audio synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Leng","year":"2022"},{"key":"ref40","article-title":"ResGrad: Residual denoising diffusion probabilistic models for text to speech","author":"Chen","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref42","article-title":"Taming visually guided sound generation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Iashin","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref44","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447246"},{"key":"ref48","first-page":"13916","article-title":"Make-an-Audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-80"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref53","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans","year":"2021"},{"key":"ref54","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref55","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":"ref56","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref57","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref59","article-title":"VoiceFixer: Toward general speech restoration with neural vocoder","author":"Liu","year":"2021"},{"key":"ref60","first-page":"591","article-title":"The million song dataset","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Bertin-Mahieux","year":"2011"},{"key":"ref61","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","volume":"14","author":"Bittner","year":"2014","journal-title":"ISMIR"},{"key":"ref62","article-title":"The MUSDB18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref63","first-page":"342","article-title":"Decoupling magnitude and phase estimation with deep ResUNet for music source separation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Kong","year":"2021"},{"key":"ref64","first-page":"776","article-title":"AudioSet: An ontology and human-labeled dataset for audio events","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Gemmeke","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref68","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","year":"2014"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3318015"},{"key":"ref70","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Engel","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref72","article-title":"LibriCount: A dataset for speaker count estimation","author":"Stter","year":"2018"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref74","first-page":"148","article-title":"Vocal imitation set: A dataset of vocally imitated sound events using the audioset ontology","volume-title":"Proc. Workshop Detection Classification Acoustic Scenes Events","author":"Kim","year":"2018"},{"key":"ref75","article-title":"Speech Commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9"},{"key":"ref77","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10768970.pdf?arnumber=10768970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:38:27Z","timestamp":1738867107000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10768970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":77,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3506286","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}