{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T14:03:29Z","timestamp":1774879409094,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1109\/icassp.2015.7178333","type":"proceedings-article","created":{"date-parts":[[2015,8,12]],"date-time":"2015-08-12T18:45:43Z","timestamp":1439405143000},"page":"2061-2065","source":"Crossref","is-referenced-by-count":21,"title":["A hybrid recurrent neural network for music transcription"],"prefix":"10.1109","author":[{"given":"Siddharth","family":"Sigtia","sequence":"first","affiliation":[]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Boulanger-Lewandowski","sequence":"additional","affiliation":[]},{"given":"Tillman","family":"Weyde","sequence":"additional","affiliation":[]},{"given":"Artur S.","family":"d'Avila Garcez","sequence":"additional","affiliation":[]},{"given":"Simon","family":"Dixon","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups","volume":"29","author":"geoffrey","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref11","article-title":"Signal Processing Methods for Music Transcription","author":"anssi","year":"2006"},{"key":"ref12","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"In Proceedings of the Eighteenth International Conference on Machine Learning ICML '01"},{"key":"ref13","first-page":"1033","article-title":"Learning recurrent neural networks with Hessian-free optimization","author":"martens","year":"2011","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref14","first-page":"175","article-title":"A classification-based polyphonic piano transcription approach using learned feature representations","author":"juhan","year":"2011","journal-title":"In International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/48317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2258012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.234"},{"key":"ref19","article-title":"d’ Avila Garcez, and Simon Dixon. An RNN-based music language model for improving automatic music transcription","author":"siddharth","year":"2014","journal-title":"In International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref4","first-page":"1159","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"2012","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287832"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854638"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638244"},{"key":"ref8","first-page":"646","article-title":"Measuring invariances in deep networks","author":"ian","year":"2009","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1109\/TASL.2009.2038819","article-title":"Multipitch estimation of piano sounds using a new probabilistic spectral smoothness principle","volume":"18","author":"valentin","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref2","article-title":"Automatic transcription of polyphonic music exploiting temporal evolution","author":"benetos","year":"2012"},{"key":"ref1","first-page":"315","article-title":"Evaluation of multiple-FO estimation and tracking systems","author":"mert","year":"2009","journal-title":"In International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref9","article-title":"Sequence transduction with recurrent neural networks","author":"alex","year":"2012","journal-title":"ICML Representation Learning Worksop"},{"key":"ref20","article-title":"Hierarchical and coupled non-negative dynamical systems with application to audio modeling","author":"umut","year":"0","journal-title":"In IEEE Workshop on Applications of Signal Processing to Audio antd Acoustics (WASPAA)"}],"event":{"name":"ICASSP 2015 - 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"South Brisbane, Queensland, Australia","start":{"date-parts":[[2015,4,19]]},"end":{"date-parts":[[2015,4,24]]}},"container-title":["2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7158221\/7177909\/07178333.pdf?arnumber=7178333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T13:32:24Z","timestamp":1498224744000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7178333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2015.7178333","relation":{},"subject":[],"published":{"date-parts":[[2015,4]]}}}