{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:03:07Z","timestamp":1784131387595,"version":"3.55.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832214","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"540-547","source":"Crossref","is-referenced-by-count":14,"title":["MDCTCodec: A Lightweight MDCT-Based Neural Audio Codec Towards High Sampling Rate and Low Bitrate Scenarios"],"prefix":"10.1109","author":[{"given":"Xiao-Hang","family":"Jiang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui-Chen","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Peng","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye-Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/25.312763"},{"issue":"10","key":"ref2","first-page":"780","article-title":"ISO\/MPEG-1 audio: A generic standard for coding of high-quality digital audio","volume":"42","author":"Brandenburg","year":"1994","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref4","article-title":"Speechtokenizer: Unified speech tokenizer for speech large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2308.16692"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref7","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref8","article-title":"High-quality, low-delay music coding in the opus codec","author":"Valin","year":"2013","journal-title":"Audio Engineering Society Convention 135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/45.1890"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref12","article-title":"Intelligent gap filling in perceptual transform coding of audio","author":"Disch","year":"2016","journal-title":"Audio Engineering Society Convention 141"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9415120"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MP.2006.1664069"},{"key":"ref16","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv:2210.13438"},{"key":"ref17","article-title":"HiFi-Codec: Groupresidual vector quantization for high fidelity audio codec","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2305.02765"},{"key":"ref18","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096056"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref23","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1563"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096553"},{"key":"ref26","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NIPS","volume":"33","author":"Kong"},{"key":"ref27","article-title":"Vocos: Closing the gap between timedomain and fourier-based neural vocoders for high-quality audio synthesis","author":"Siuzdak","year":"2023","journal-title":"arXiv preprint arXiv:2306.00814"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref29","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint arXiv:1606.08415"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref31","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"in Proc. ICML","volume":"30","author":"Maas"},{"key":"ref32","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref35","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832214.pdf?arnumber=10832214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:03Z","timestamp":1737100203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832214","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}