{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:18:12Z","timestamp":1783401492344,"version":"3.54.6"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414721","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7153-7157","source":"Crossref","is-referenced-by-count":21,"title":["Cascaded Time + Time-Frequency Unet For Speech Enhancement: Jointly Addressing Clipping, Codec Distortions, And Gaps"],"prefix":"10.1109","author":[{"given":"Arun Asokan","family":"Nair","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhito","family":"Koishida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054563"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.21437\/Interspeech.2017-1465","article-title":"A fully convolutional neural network for speech enhancement","author":"park","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953226"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref14","article-title":"A survey and an extensive evaluation of popular audio declipping methods","author":"z\u00e1vi\u0161ka","year":"2020"},{"key":"ref15","article-title":"Image to image translation based on convolutional neural network approach for speech declipping","author":"kashani","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937287"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2887337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04158-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref3","author":"wiener","year":"1950","journal-title":"Extrapolation Interpolation and Smoothing of Stationary Time Series with Engineering Applications"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-88"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref8","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"key":"ref2","volume":"62","author":"lee","year":"1988","journal-title":"Automatic Speech Recognition The Development of the SPHINX System"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref20","article-title":"On deep speech packet loss concealment: A mini-survey","author":"mohamed","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909077"},{"key":"ref21","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref24","year":"0","journal-title":"FFmpeg a complete cross-platform solution to record convert and stream audio and video"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref25","article-title":"Computer networking from lans to wans: Hardware, software, and security","author":"kenneth","year":"2010"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414721.pdf?arnumber=9414721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:50Z","timestamp":1652197250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414721","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}