{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:13:30Z","timestamp":1778948010603,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096707","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":11,"title":["A Phoneme-Informed Neural Network Model For Note-Level Singing Transcription"],"prefix":"10.1109","author":[{"given":"Sangeon","family":"Yong","sequence":"first","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Su","sequence":"additional","affiliation":[{"name":"Academia Sinica,Institute of Information Science,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref24","first-page":"431","article-title":"DALI: A large dataset of synchronized audio, lyrics, and notes, automatically created using teacher-student machine learning paradigm","author":"meseguer-brocal","year":"2018","journal-title":"Proc of the 19th Int Society for Music Information Retrieval"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03391"},{"key":"ref15","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","author":"hawthorne","year":"2019","journal-title":"Int Conf on Learning Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1676"},{"key":"ref20","first-page":"367","article-title":"mir_eval: A transparent implementation of common MIR metrics","author":"raffel","year":"2014","journal-title":"Proc of the 15th Int Society for Music Information Retrieval"},{"key":"ref11","first-page":"454","article-title":"Polyphonic piano transcription using autoregressive multi-state note model","author":"kwon","year":"2020","journal-title":"Proc of the 21st Int Society for Music Information Retrieval Conf"},{"key":"ref22","article-title":"Computer-aided melody note transcription using the tony software: Accuracy and efficiency","author":"mauch","year":"2015","journal-title":"Proc of Sound and Music Computing"},{"key":"ref10","first-page":"475","article-title":"On the potential of simple framewise approaches to piano transcription","author":"kelz","year":"2016","journal-title":"Proc of the 17th Int Society for Music Information Retrieval Conf"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Int Conf on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref1","first-page":"50","article-title":"Onsets and frames: dual-objective piano transcription","author":"hawthorne","year":"2018","journal-title":"Proc of the 19th Int Society for Music Information Retrieval Conf"},{"key":"ref17","article-title":"Children’s song dataset for singing voice research","author":"choi","year":"2020","journal-title":"ISMIR Late Breaking and Demo Papers"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref19","article-title":"The cmu pronouncing dictionary","year":"0"},{"key":"ref18","article-title":"TIMIT acoustic-phonetic continuous speech corpus","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium Philadelphia"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746684"},{"key":"ref7","first-page":"293","article-title":"VOCANO: A note transcription framework for sining voice in polyphonic music","author":"hsu","year":"2021","journal-title":"Proc of the 22nd Int Society for Music Information Retrieval"},{"key":"ref9","first-page":"17","article-title":"Phoneme-informed note segmentation of monophonic vocal music","author":"li","year":"2021","journal-title":"Proc of the 2nd Workshop on NLP for Music and Spoken Audio (NLP4MusA)"},{"key":"ref4","first-page":"133","article-title":"Onset detection revisited","author":"dixon","year":"2006","journal-title":"Proc of the 9th Int Conf on Digital Audio Effects"},{"key":"ref3","first-page":"567","article-title":"Evaluation framework for automatic singing transcription","author":"molina","year":"2014","journal-title":"Proc of the 15th Int Society for Music Information Retrieval Conf"},{"key":"ref6","first-page":"900","article-title":"Hierarchical classification networks for singing voice segmentation and transcription","author":"fu","year":"2019","journal-title":"Proc of the 20th Int Society for Music Information Retrieval"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683024"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096707.pdf?arnumber=10096707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:56:59Z","timestamp":1699901819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096707","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}