{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T19:06:20Z","timestamp":1775847980460,"version":"3.50.1"},"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\/icassp40776.2020.9053669","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"536-540","source":"Crossref","is-referenced-by-count":31,"title":["Data-Driven Harmonic Filters for Audio Representation Learning"],"prefix":"10.1109","author":[{"given":"Minz","family":"Won","sequence":"first","affiliation":[]},{"given":"Sanghyuk","family":"Chun","sequence":"additional","affiliation":[]},{"given":"Oriol","family":"Nieto","sequence":"additional","affiliation":[]},{"given":"Xavier","family":"Serrc","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Data-driven design of perfect reconstruction filterbank for dnn-based sound source enhancement","author":"takeuchi","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref12","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"International Society for Music Information Retrieval Conference"},{"key":"ref13","article-title":"Automatic music tagging with harmonic cnn","author":"won","year":"2019","journal-title":"Late Breaking Demo in the International Society for Music Information Retrieval Conference"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref15","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"32nd International Conference on Machine Learning"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref17","article-title":"Toward interpretable music tagging with self-attention","author":"won","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref18","article-title":"A neural attention model for speech command recognition","author":"de andrade","year":"2018","journal-title":"arXiv preprint arXiv 1808 05089"},{"key":"ref19","article-title":"Surrey-cvssp system for dcase2017 challenge task4","author":"xu","year":"2017","journal-title":"Detection and Classification of Acoustic Scenes and Events"},{"key":"ref4","article-title":"Very deep convolutional neural networks for raw waveforms","author":"dai","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref3","article-title":"Learning the speech front-end with raw waveform cldnns","author":"sainath","year":"2015","journal-title":"Annual Conference of the International Speech Communication Association"},{"key":"ref6","author":"sethares","year":"2005","journal-title":"Tuning Timbre Spectrum Scale"},{"key":"ref5","article-title":"End-to-end learning for music audio tagging at scale","author":"pons","year":"2018","journal-title":"International Society for Music Information Retrieval Conference"},{"key":"ref8","article-title":"A deep neural network integrated with filterbank learning for speech recognition","author":"seki","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref7","article-title":"Adaptive front-ends for end-to-end source separation","author":"venkataramani","year":"2017","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref2","article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","author":"lee","year":"2017","journal-title":"Sound and Music Computing Conference"},{"key":"ref1","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref9","article-title":"Basic filters for convolutional neural networks applied to music: Training or design?","author":"dorfler","year":"2018","journal-title":"Neural Computing and Applications"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909479"},{"key":"ref22","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018","journal-title":"arXiv preprint arXiv 1804 00209"},{"key":"ref21","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"International Society for Music Information Retrieval Conference"},{"key":"ref24","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref23","article-title":"Dcase 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"Detection and Classification of Acoustic Scenes and Events"}],"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\/09053669.pdf?arnumber=9053669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:44Z","timestamp":1656375104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053669","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}