{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:05:12Z","timestamp":1760598312189,"version":"3.37.3"},"reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3482359","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:43:59Z","timestamp":1729187039000},"page":"159239-159251","source":"Crossref","is-referenced-by-count":2,"title":["A Bitrate-Scalable Variational Recurrent Mel-Spectrogram Coder for Real-Time Resynthesis-Based Speech Coding"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6446-0039","authenticated-orcid":false,"given":"Benjamin","family":"Stahl","sequence":"first","affiliation":[{"name":"Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria"}]},{"given":"Simon","family":"Windtner","sequence":"additional","affiliation":[{"name":"Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9205-209X","authenticated-orcid":false,"given":"Alois","family":"Sontacchi","sequence":"additional","affiliation":[{"name":"Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1973.tb02007.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1975.1092759"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref5","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"30","author":"Oord"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref8","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref11","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. 33 (NeurIPS)","author":"Kong"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-430"},{"key":"ref13","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref15","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv:2210.13438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-487"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5626\/JOK.2021.48.8.940"},{"key":"ref21","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Annu. Conf. Neural Inf. Process. Syst.","author":"Bengio"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2200000089"},{"key":"ref23","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chung"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref28","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Kumar"},{"key":"ref29","first-page":"1","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lee"},{"key":"ref30","first-page":"1583","article-title":"Neural networks fail to learn periodic functions and how to fix it","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ziyin"},{"key":"ref31","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref32","article-title":"Simple and effective VAE training with calibrated decoders","author":"Rybkin","year":"2020","journal-title":"arXiv:2006.13202"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"volume-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Veaux","key":"ref34"},{"volume-title":"TSP Speech Database, Version 2","year":"2018","author":"Kabal","key":"ref35"},{"key":"ref36","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref40","first-page":"1","article-title":"High-quality, low-delay music coding in the Opus codec","volume-title":"Proc. 135th Audio Eng. Soc. Conv.","author":"Valin"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"volume-title":"Method for the Subjective Assessment of Intermediate Quality Level of Coding Systems","year":"2015","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10720741.pdf?arnumber=10720741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:59:02Z","timestamp":1732669142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3482359","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}