{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:42:45Z","timestamp":1781592165446,"version":"3.54.5"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"Ministry of Education, Youth, and Sports Project, conducted at the VSB\u2013Technical University of Ostrava, Czech Republic","award":["LM2015070"],"award-info":[{"award-number":["LM2015070"]}]},{"name":"Ministry of Education, Youth, and Sports Project, conducted at the VSB\u2013Technical University of Ostrava, Czech Republic","award":["SGS SP2019\/41"],"award-info":[{"award-number":["SGS SP2019\/41"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2920663","type":"journal-article","created":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T15:56:39Z","timestamp":1559663799000},"page":"75081-75089","source":"Crossref","is-referenced-by-count":5,"title":["DeepVoCoder: A CNN Model for Compression and Coding of Narrow Band Speech"],"prefix":"10.1109","volume":"7","author":[{"given":"Hacer Yalim","family":"Keles","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Rozhon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4365-8286","authenticated-orcid":false,"given":"H.","family":"Gokhan Ilk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miroslav","family":"Voznak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref12","author":"rowe","year":"2011","journal-title":"Codec 2-open source speech coding at 2400 bits\/s and below"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.08.002"},{"key":"ref16","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref18","article-title":"Transferring rich feature hierarchies for robust visual tracking","author":"wang","year":"2015","journal-title":"arXiv 1501 04587"},{"key":"ref19","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"2013","journal-title":"Proc ICML"},{"key":"ref28","year":"2001","journal-title":"Perceptual Evaluation of Speech Quality (PESQ) An Objective Method for End-to-End Speech Quality Assessment of Narrow-Band Telephone Networks and Speech Codecs"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.1995189"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3813\/AAA.918465"},{"key":"ref3","article-title":"Wavenet based low rate speech coding","author":"kleijn","year":"2017","journal-title":"arXiv 1712 01120"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref29","year":"2019","journal-title":"MIT Former Media Lab Music Mind and Machine Group SQAM (Sound Quality Assessment Material) Database"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164946"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/29.1651"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1970.tb04297.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.540325"},{"key":"ref1","author":"berger","year":"1971","journal-title":"Rate Distortion Theory A Mathematical Basis for Data Compression"},{"key":"ref20","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref22","year":"1988","journal-title":"Pulse Code Modulation of Voice Frequencies"},{"key":"ref21","year":"2019","journal-title":"Vox Forge Open Source Speech Corpus"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2017","journal-title":"arXiv 1412 6980"},{"key":"ref23","author":"chollet","year":"2015","journal-title":"Keras"},{"key":"ref26","year":"2015","journal-title":"Transmission Systems and Media Digital Systems and Networks"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08730308.pdf?arnumber=8730308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:54:13Z","timestamp":1641988453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8730308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2920663","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}