{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:13Z","timestamp":1775230033710,"version":"3.50.1"},"reference-count":21,"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\/waspaa52581.2021.9632723","type":"proceedings-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T21:12:28Z","timestamp":1639429948000},"page":"316-320","source":"Crossref","is-referenced-by-count":17,"title":["Harp-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding"],"prefix":"10.1109","author":[{"given":"Darius","family":"Petermann","sequence":"first","affiliation":[]},{"given":"Seungkwon","family":"Beack","sequence":"additional","affiliation":[]},{"given":"Minje","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref11","article-title":"A real-time wideband neural vocoder at 1.6 kb\/s using LPCNet","year":"0","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3039765"},{"key":"ref13","article-title":"Cas-caded cross-module residual learning towards lightweight end-to-end speech coding","author":"zhen","year":"0","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref14","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref15","article-title":"Wave-u-net: A multiscale neural network for end-to-end audio source separation","author":"stoller","year":"0","journal-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref17","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","author":"agustsson","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref18","article-title":"Singing voice separation with deep u-net convolutional networks","author":"jansson","year":"0","journal-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref4","article-title":"Definition of the opus audio codec","author":"valin","year":"2012","journal-title":"IETF"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref6","article-title":"Effi-cient and scalable neural residual waveform coding with collaborative quantization","author":"zhen","year":"0","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref7","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref2","year":"2011"},{"key":"ref1","year":"2011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109381"},{"key":"ref21","year":"2003"}],"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\/09632723.pdf?arnumber=9632723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:23Z","timestamp":1652201663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/waspaa52581.2021.9632723","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}