{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:15:20Z","timestamp":1776885320812,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"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":[[2021,10,17]]},"DOI":"10.1109\/waspaa52581.2021.9632750","type":"proceedings-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T21:12:28Z","timestamp":1639429948000},"page":"66-70","source":"Crossref","is-referenced-by-count":19,"title":["A Streamwise Gan Vocoder for Wideband Speech Coding at Very Low Bit Rate"],"prefix":"10.1109","author":[{"given":"Ahmed","family":"Mustafa","sequence":"first","affiliation":[]},{"given":"Jan","family":"Buthe","sequence":"additional","affiliation":[]},{"given":"Srikanth","family":"Korse","sequence":"additional","affiliation":[]},{"given":"Kishan","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Guillaume","family":"Fuchs","sequence":"additional","affiliation":[]},{"given":"Nicola","family":"Pia","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref12","article-title":"High fidelity speech synthesis with adversarial networks","author":"binkowski","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref13","first-page":"7155","article-title":"High-quality Speech Coding with SampleRNN","author":"klejsa","year":"0","journal-title":"ICASSP 2019 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1003"},{"key":"ref17","author":"ulyanov","year":"2016","journal-title":"Instance normalization The missing ingredient for fast stylization"},{"key":"ref18","article-title":"High-fidelity generative image compression","volume":"33","author":"mentzer","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref27","first-page":"366","article-title":"Perceptual Objective Listening Quality Assessment (POLQA), the third generation ITU - T standard for end-to-end speech quality measurement part I - temporal alignment","volume":"61","author":"beerends","year":"2013","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref3","author":"van den oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref5","first-page":"2410","article-title":"Effi-cient neural audio synthesis","volume":"80","author":"kalchbrenner","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref8","first-page":"14910","article-title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","volume":"32","author":"kumar","year":"0","journal-title":"Adv in NeurIPS"},{"key":"ref7","first-page":"2672","article-title":"Generative Adversarial Nets","volume":"27","author":"goodfellow","year":"0","journal-title":"Adv in NeurIPS"},{"key":"ref2","first-page":"3406","article-title":"A Real-Time Wideband Neural Vocoder at 1.6 kb\/s Using LPCNet","author":"valin","year":"0","journal-title":"INTERSPEECH 2019 20th Annual Conference of the International Speech Communication Association"},{"key":"ref9","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"ICLRE"},{"key":"ref21","author":"yamagishi","year":"2019","journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit"},{"key":"ref24","year":"2009","journal-title":"Speech Codec Speech Processing Functions Adaptive Multi-Rate - Wideband (AMR-WB) Speech Codec Transcoding Functions"},{"key":"ref23","year":"2003","journal-title":"Method for the Subjective Assessment of Intermediate Quality Levels of Coding Systems"},{"key":"ref26","year":"2021","journal-title":"Google"},{"key":"ref25","year":"2014","journal-title":"TS 26 445 EVS Codec Detailed Algorithmic Description 3GPP Technical Specification (Release 12)"}],"event":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2021,10,17]]},"end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9632687\/9632666\/09632750.pdf?arnumber=9632750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:25Z","timestamp":1652201665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/waspaa52581.2021.9632750","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}