{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T23:26:38Z","timestamp":1782170798593,"version":"3.54.5"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053727","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6489-6493","source":"Crossref","is-referenced-by-count":36,"title":["Multi-Time-Scale Convolution for Emotion Recognition from Speech Audio Signals"],"prefix":"10.1109","author":[{"given":"Eric","family":"Guizzo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tillman","family":"Weyde","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack Barnett","family":"Leveson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"121","article-title":"Exploring data augmentation for improved singing voice detection with neural networks","author":"schl\u00fcter","year":"2015","journal-title":"ISMIR"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object detection with discriminatively trained part-based models","volume":"32","author":"felzenszwalb","year":"2009","journal-title":"IEEE PAMI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738904"},{"key":"ref15","article-title":"Learning multi-scale features directly from waveforms","author":"zhu","year":"2016"},{"key":"ref16","article-title":"Locally scale-invariant convolutional neural networks","author":"kanazawa","year":"2014","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref17","article-title":"A database of german emotional speech","author":"burkhardt","year":"2005","journal-title":"Eurospeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref19","author":"dupuis","year":"2010","journal-title":"Toronto Emotional Speech Set (TESS)"},{"key":"ref4","first-page":"63","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"ISMIR"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-3","article-title":"Analysis of cnn-based speech recognition system using raw speech as input","author":"palaz","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-211"},{"key":"ref1","first-page":"745","article-title":"Singing voice separation with deep u-net convolutional networks","author":"jansson","year":"2017","journal-title":"ISMIR"},{"key":"ref9","first-page":"248","article-title":"A software framework for musical data augmentation","author":"mcfee","year":"2015","journal-title":"ISMIR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2016.7843306"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5539-3"},{"key":"ref24","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref23","article-title":"Speaker independent emotion recognition by early fusion of acoustic and linguistic features within ensembles","author":"schuller","year":"2005","journal-title":"Eurospeech"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053727.pdf?arnumber=9053727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:27:05Z","timestamp":1696015625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053727","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}