{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T15:40:06Z","timestamp":1767109206916,"version":"3.37.3"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1109\/access.2021.3089565","type":"journal-article","created":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T19:52:35Z","timestamp":1623786755000},"page":"94923-94933","source":"Crossref","is-referenced-by-count":11,"title":["Full-Band LPCNet: A Real-Time Neural Vocoder for 48 kHz Audio With a CPU"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2935-668X","authenticated-orcid":false,"given":"Keisuke","family":"Matsubara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9913-4647","authenticated-orcid":false,"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9808-0250","authenticated-orcid":false,"given":"Ryoichi","family":"Takashima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5005-7679","authenticated-orcid":false,"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinori","family":"Shiga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Subjective performance assessment of telephone-band and wideband digital codecs","year":"1990","key":"ref73"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.01.007"},{"key":"ref71","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref39","article-title":"HiFiSinger: Towards high-fidelity neural singing voice synthesis","author":"chen","year":"2020","journal-title":"arXiv 2009 01776"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7075"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462237"},{"key":"ref32","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-20"},{"key":"ref30","first-page":"2473","article-title":"GlottDNN—A full-band glottal Vocoder for statistical parametric speech synthesis","author":"airaksinen","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054490"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054466"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053642"},{"key":"ref34","first-page":"13","article-title":"Deep neural network based real-time speech vocoder with periodic and aperiodic inputs","author":"oura","year":"2019","journal-title":"Proc SSW"},{"key":"ref60","first-page":"131","article-title":"Recent development of open-source speech recognition engine Julius","author":"lee","year":"2009","journal-title":"Proc APSIPAASC"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.140"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref28","first-page":"2672","article-title":"Generative adversaria nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref27","first-page":"1","article-title":"ByteSing: A Chinese singing voice synthesis system using duration allocated encoder-decoder acoustic models and WaveRNN vocoders","author":"gu","year":"2021","journal-title":"Proc ISCSLP"},{"key":"ref65","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref68","first-page":"6729","article-title":"Transformer-based text-to-speech with weighted forced attention","author":"okamoto","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc SSW"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref22","first-page":"492","article-title":"Multi-band melgan: Faster waveform generation for high-quality text-to-speech","author":"yang","year":"2021","journal-title":"Proc SLT"},{"key":"ref21","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref24","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"Proc ICLR"},{"key":"ref23","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"Proc ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1563"},{"key":"ref25","first-page":"6054","article-title":"LVCNet: Efficient condition-dependent modeling network for waveform generation","author":"zeng","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2041"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref58","article-title":"High-quality, low-delay music coding in the opus codec","author":"valin","year":"2013","journal-title":"Proc 135th AES Conv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"journal-title":"Pulse Code Modulation (PCM) of Voice Frequencies","year":"1988","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1975.9792"},{"journal-title":"An Introduction to the Psychology of Hearing","year":"2013","author":"moore","key":"ref54"},{"key":"ref53","first-page":"7058","article-title":"High-intelligibility speech synthesis for dysarthric speakers with LPCNet -based TTS and CycleVAE-based VC","author":"matsubara","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.65"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref40","first-page":"6049","article-title":"Periodnet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components","author":"hono","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref13","first-page":"3370","article-title":"FloWaveNet: A generative flow for raw audio","author":"kim","year":"2019","journal-title":"Proc ICML"},{"key":"ref14","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref16","first-page":"7586","article-title":"Non-autoregressive neural text-to-speech","author":"peng","year":"2020","journal-title":"Proc ICML"},{"key":"ref17","first-page":"7706","article-title":"WaveFlow: A compact flow-based model for raw audio","author":"ping","year":"2020","journal-title":"Proc ICML"},{"key":"ref18","article-title":"High fidelity speech synthesis with adversarial networks","author":"bi?kowski","year":"2020","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835720"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref8","first-page":"2415","article-title":"Efficient neutal audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref7","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1463"},{"key":"ref9","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref46","first-page":"6734","article-title":"Improving end-to-end speech synthesis with local recurrent neural network enhanced transformer","author":"zheng","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053337"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2169"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1642"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1736"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053704"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09455356.pdf?arnumber=9455356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T19:43:26Z","timestamp":1643226206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9455356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3089565","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}