{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:46:29Z","timestamp":1765039589584,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413732","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"546-550","source":"Crossref","is-referenced-by-count":2,"title":["Instrument Classification of Solo Sheet Music Images"],"prefix":"10.1109","author":[{"given":"Kevin","family":"Ji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TJ","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3079","article-title":"Semi-supervised sequence learning","author":"dai","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc of the Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref12","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"article-title":"Language models are few-shot learners","year":"2020","author":"brown","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"article-title":"Retrieval-augmented language model pretraining","year":"2020","author":"guu","key":"ref15"},{"key":"ref16","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"916","article-title":"MIDI passage retrieval using cell phone pictures of sheet music","author":"yang","year":"2019","journal-title":"Proc of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref18","article-title":"Regularizing and optimizing lstm language models","author":"merity","year":"2018","journal-title":"International Conference on Learning Representations"},{"article-title":"RoBERTa: A robustly optimized BERT pretraining approach","year":"2019","author":"liu","key":"ref19"},{"key":"ref4","first-page":"577","article-title":"Jazz solo instrument classification with convolutional neural networks, source separation, and transfer learning","author":"gomez","year":"2018","journal-title":"Proc of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref3","first-page":"569","article-title":"Instrument activity detection in polyphonic music using deep neural networks","author":"gururani","year":"2018","journal-title":"Proc of the International Society for Music Information Retrieval Conference (ISMIR)"},{"article-title":"Learning multi-instrument classification with partial labels","year":"2020","author":"anhari","key":"ref6"},{"key":"ref5","first-page":"83","article-title":"An attention mechanism for musical instrument recognition","author":"gururani","year":"2019","journal-title":"Proc of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref8","first-page":"176","article-title":"Composer style classification of piano sheet music images using language model pretraining","author":"tsai","year":"2020","journal-title":"Proc of the International Society for Music Information Retrieval Conference (ISMIR)"},{"article-title":"Receptive-field regularized CNNs for music classification and tagging","year":"2020","author":"koutini","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2632307"},{"key":"ref1","first-page":"438","article-title":"OpenMIC-2018: An open data-set for multiple instrument recognition","author":"humphrey","year":"2018","journal-title":"Proc of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref20","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"gage","year":"1994","journal-title":"C Users Journal"},{"article-title":"A disciplined approach to neural network hyper-parameters: Part 1–learning rate, batch size, momentum, and weight decay","year":"2018","author":"smith","key":"ref22"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"549","article-title":"Convolutional composer classification","author":"verma","year":"2019","journal-title":"Proc of the International Society for Music Information Retrieval Conference (ISMIR)"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413732.pdf?arnumber=9413732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:01Z","timestamp":1652197261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413732","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}