{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:04:39Z","timestamp":1776841479746,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461524","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"3136-3140","source":"Crossref","is-referenced-by-count":25,"title":["Content-Based Representations of Audio Using Siamese Neural Networks"],"prefix":"10.1109","author":[{"given":"Pranay","family":"Manocha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan","family":"Badlani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankit","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Elizalde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICGTSPICC.2016.7955371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref12","author":"ellis","year":"2009","journal-title":"Robust Landmark-based Audio Fingerprinting"},{"key":"ref13","first-page":"107","article-title":"A highly robust audio fingerprinting system","volume":"2002","author":"haitsma","year":"2002","journal-title":"ISMIR"},{"key":"ref14","first-page":"7","article-title":"An industrial strength audio search algorithm","volume":"2003","author":"wang","year":"2003","journal-title":"Ismir Washington DC"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:19949924"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101181"},{"key":"ref17","first-page":"2386","article-title":"Audio fingerprinting to identify multiple videos of an event","author":"cotton","year":"2010","journal-title":"Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","first-page":"i","article-title":"Fingerprinting to identify repeated sound events in long-duration personal audio recordings","volume":"1","author":"ogle","year":"2007","journal-title":"Acoustics Speech and Signal Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref4","first-page":"2460","author":"qi","year":"2016","journal-title":"Sketch-based image retrieval via siamese convolutional neural network"},{"key":"ref27","article-title":"A dataset and taxonomy for urban sound research","author":"salamon","year":"2014","journal-title":"22st ACM International Conference on Multimedia (ACM-MM'14)"},{"key":"ref3","author":"eng-jon","year":"2017","journal-title":"Siamese network of deep fisher-vector descriptors for image retrieval"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009000"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/93.556537"},{"key":"ref8","first-page":"138","article-title":"Content-based retrieval of music and audio","volume":"3229","author":"foote","year":"1997","journal-title":"Multimedia Storage and Archiving Systems II International Society for Optics and Photonics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"ref2","first-page":"5005","author":"wang","year":"2016","journal-title":"Learning deep structure-preserving image-text embeddings"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460115"},{"key":"ref1","first-page":"905","article-title":"Detecting sound objects in audio recordings","author":"kumar","year":"2014","journal-title":"Signal Processing Conference (EUSIPCO)"},{"key":"ref20","first-page":"2786","article-title":"Siamese recurrent architectures for learning sentence similarity","author":"mueller","year":"2016","journal-title":"AAAI"},{"key":"ref22","first-page":"234","article-title":"Large-scale content-based matching of midi and audio files","author":"raffel","year":"2015","journal-title":"ISMIR"},{"key":"ref21","first-page":"737","article-title":"Signature verification using a&#x201D; siamese&#x201D; time delay neural network","author":"bromley","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"298","article-title":"Extracting speaker-specific information with a regularized siamese deep network","author":"chen","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-811"},{"key":"ref26","first-page":"1","article-title":"Environmental sound classification with convolutional neural networks","author":"piczak","year":"2015","journal-title":"IEEE Workshop on Machine Learning for Signal Processing (MLSP)"},{"key":"ref25","first-page":"1735","article-title":"Dimensional-ity reduction by learning an invariant mapping","volume":"2","author":"hadsell","year":"2006","journal-title":"Computer Vision and Pattern Recognition"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461524.pdf?arnumber=8461524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:58:57Z","timestamp":1598223537000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461524","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}