{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:52:35Z","timestamp":1774965155208,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"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":[[2021,10,25]]},"DOI":"10.1109\/mlsp52302.2021.9596082","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T22:53:58Z","timestamp":1637016838000},"page":"1-6","source":"Crossref","is-referenced-by-count":28,"title":["Self-Attention for Audio Super-Resolution"],"prefix":"10.1109","author":[{"given":"Carraz Nathanael","family":"Rakotonirina","sequence":"first","affiliation":[{"name":"Université d’ Antananarivo,Madagascar"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref32","article-title":"Neural combinatorial optimization with reinforcement learning","author":"irwan","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref31","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"Generative adversarial networks","author":"ian","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937186"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683169"},{"key":"ref10","author":"yamagishi","year":"2012","journal-title":"English multi-speaker corpus for cstr voice cloning toolkit"},{"key":"ref11","article-title":"Samplernn: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref40","first-page":"1874","article-title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","author":"wenzhe","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref12","author":"larsen","year":"2005","journal-title":"Audio Bandwidth Extension Application of Psychoacoustics Signal Processing and Loudspeaker Design"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-528"},{"key":"ref14","first-page":"375","article-title":"Beta process sparse nonnegative matrix factorization for music","author":"dawen","year":"2013","journal-title":"ISMIR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2015.7251945"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/89.326637"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947504"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862114"},{"key":"ref19","author":"bradbury","year":"2000","journal-title":"Linear Predictive Coding"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"jeffrey","year":"1990","journal-title":"Cognitive Science"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3043"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"yann","year":"1989","journal-title":"Neural Computation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462588"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-555"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","article-title":"Nu-gan: High resolution neural upsampling with gan","author":"kumar","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref7","article-title":"Audio super-resolution using neural nets","author":"kuleshov","year":"2017","journal-title":"ICLR (workshop track)"},{"key":"ref2","article-title":"Bandwidth extension of audio signals by spectral band replication","author":"ekstrand","year":"2002","journal-title":"Proceedings of the 1 st IEEE Benelux Workshop on Model Based Processing and Coding of Audio (MPCA'02"},{"key":"ref9","first-page":"5998","article-title":"Attention is all you need","author":"ashish","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"10287","article-title":"Temporal film: Capturing long-range sequence dependencies with feature-wise modulations","author":"birnbaum","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462049"},{"key":"ref22","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706637"},{"key":"ref42","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Improved speech enhancement with the wave-u-net","author":"macartney","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref41","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162849"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2605"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682215"}],"event":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Gold Coast, Australia","start":{"date-parts":[[2021,10,25]]},"end":{"date-parts":[[2021,10,28]]}},"container-title":["2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9596063\/9596068\/09596082.pdf?arnumber=9596082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:30:09Z","timestamp":1659483009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9596082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,25]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/mlsp52302.2021.9596082","relation":{},"subject":[],"published":{"date-parts":[[2021,10,25]]}}}