{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T09:00:11Z","timestamp":1767085211697},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461686","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"2241-2245","source":"Crossref","is-referenced-by-count":29,"title":["Invariances and Data Augmentation for Supervised Music Transcription"],"prefix":"10.1109","author":[{"given":"John","family":"Thickstun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaid","family":"Harchaoui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dean P.","family":"Foster","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sham M.","family":"Kakade","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Escaping from the abyss of manual annotation: New methodology of building polyphonic datasets for automatic music transcription","author":"su","year":"2015","journal-title":"International Symposium on Computer Music Multidisciplinary Research (CMMR)"},{"key":"ref11","article-title":"A classification-based polyphonic piano transcription approach using learned feature representations","author":"nam","year":"2011","journal-title":"International Society for Music Information Retrieval (IS-MIR)"},{"journal-title":"Deep complex networks","year":"2017","author":"trabelsi","key":"ref12"},{"key":"ref13","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"The International Society for Music Information Retrieval (ISMIR)"},{"key":"ref14","article-title":"Designing efficient architectures for modeling temporal features with convolutional neural networks","author":"pons","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref15","article-title":"A hybrid recurrent neural network for music transcription","author":"sigtia","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2016.2533858","article-title":"An end-to-end neural network for polyphonic piano music transcription","author":"sigtia","year":"2016","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref17","article-title":"Best practices for convolutional neural networks applied to visual document analysis","author":"simard","year":"2003","journal-title":"International Conference on Document Analysis and Recognition (ICDAR)"},{"key":"ref18","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref19","article-title":"A software framework for musical data augmentation","author":"mcfee","year":"2015","journal-title":"The International Society for Music Information Retrieval (ISMIR)"},{"key":"ref4","article-title":"Rwc music database: Music genre database and musical instrument sound database","author":"goto","year":"2003","journal-title":"The International Society for Music Information Retrieval (ISMIR)"},{"key":"ref3","article-title":"Mirex 2017: Multi-instrumental end-to-end convolutional neural network for multiple f0 estimation","author":"mita","year":"2017","journal-title":"Music Information Retrieval Evaluation eX-change"},{"journal-title":"Learning-Based Methods for Comparing Sequences with Applications to Audio-to-MIDI Alignment and Matching","year":"2016","author":"raffel","key":"ref6"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/TASL.2009.2038819","article-title":"Multipitch estimation of piano sounds using a new probabilistic spectral smoothness principle","author":"emiya","year":"2010","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref8","article-title":"End-to-end learning for music audio","author":"dieleman","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","article-title":"Learning features of music from scratch","author":"thickstun","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref2","article-title":"Multiple fundamental frequency estimation & tracking submission for mirex 2016","author":"marolt","year":"2016","journal-title":"Music information retrieval evaluation exchange (Mirex)"},{"key":"ref1","article-title":"Music transcription with a convolutional neural network 2016","author":"troxel","year":"2016","journal-title":"Music information retrieval evaluation exchange (Mirex)"},{"key":"ref9","article-title":"A discriminative model for polyphonic piano transcription","author":"poliner","year":"2007","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1561\/2000000001","article-title":"Introduction to digital speech processing","author":"rabiner","year":"2007","journal-title":"Foundations and Trends in Signal Processing"},{"journal-title":"Melodyne","year":"0","key":"ref22"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/5.58325","article-title":"The self-organizing map","author":"kohonen","year":"1990","journal-title":"Proceedings of the IEEE"},{"key":"ref24","article-title":"mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref23","article-title":"Scikit-learn: Machine learning in python","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research (JMLR)"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","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\/08461686.pdf?arnumber=8461686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:43:08Z","timestamp":1598247788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461686","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}