{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:44:42Z","timestamp":1772909082619,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1617107"],"award-info":[{"award-number":["1617107"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1617497"],"award-info":[{"award-number":["1617497"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1109\/taslp.2018.2868428","type":"journal-article","created":{"date-parts":[[2018,9,3]],"date-time":"2018-09-03T22:51:35Z","timestamp":1536015095000},"page":"429-441","source":"Crossref","is-referenced-by-count":32,"title":["Siamese Style Convolutional Neural Networks for Sound Search by Vocal Imitation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0465-6341","authenticated-orcid":false,"given":"Yichi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Bryan","family":"Pardo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8334-9974","authenticated-orcid":false,"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1177\/107385802237175"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref32","first-page":"1","article-title":"Understanding representations learned in deep architectures","author":"erhan","year":"2010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref30","article-title":"Understanding and visualizing convolutional neural networks","year":"2017"},{"key":"ref37","first-page":"1","article-title":"Constant-Q transform toolbox for music processing","author":"sch\u00f6rkhuber","year":"0","journal-title":"Proc 7th Sound Music Comput Conf"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref35","first-page":"1","article-title":"Deep learning for spoken language identification","author":"montavon","year":"0","journal-title":"Proc NIPS Workshop Deep Learn Speech Recognit Related Appl"},{"key":"ref34","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2016.0013"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1147\/sj.164.0324"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082307"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390397"},{"key":"ref14","first-page":"7","article-title":"An industrial strength audio search algorithm","author":"wang","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853675"},{"key":"ref16","first-page":"427","article-title":"Known artist live song id: A hashprint approach","author":"tsai","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/217279.215273"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20532"},{"key":"ref19","first-page":"170","article-title":"Query-by-beating-boxing: Music retrieval for the DJ","author":"kapur","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref28","first-page":"3279","article-title":"Matchnet: Unifying feature and metric learning for patch-based matching","author":"han","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recog"},{"key":"ref4","first-page":"1","article-title":"Sound retrieval from voice imitation queries in collaborative databases","author":"blancas","year":"0","journal-title":"Proc Audio Eng Soc 53rd Conf Semantic Audio (AES53)"},{"key":"ref27","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"bertinetto","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref3","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461729"},{"key":"ref29","first-page":"298","article-title":"Extracting speaker-specific information with a regularized siamese deep network","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702387"},{"key":"ref7","first-page":"737","article-title":"Signature verification using a ‘siamese’ time delay neural network","author":"bromley","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","article-title":"Audio query by example using similarity measures between probability density functions of features","volume":"2010","author":"hel\u00e9n","year":"2009","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472081"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324316"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.1945807"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-005-0321-9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.3642604"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952219"},{"key":"ref21","first-page":"1","article-title":"Querying freesound with a microphone","author":"roma","year":"0","journal-title":"Proc 1st Web Audio Conf"},{"key":"ref42","article-title":"Evaluating web-based question answering systems","volume":"1001","author":"radev","year":"2002","journal-title":"Ann Arbor"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref41","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1613\/jair.614"},{"key":"ref26","first-page":"1","article-title":"Siamese neural networks for one-shot image recognition","author":"koch","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/6570655\/8552740\/8453811-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8552740\/08453811.pdf?arnumber=8453811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:45:01Z","timestamp":1657745101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8453811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":47,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2868428","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}