{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T03:13:56Z","timestamp":1780110836510,"version":"3.54.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682582","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"396-400","source":"Crossref","is-referenced-by-count":20,"title":["Automatic Lyrics-to-audio Alignment on Polyphonic Music Using Singing-adapted Acoustic Models"],"prefix":"10.1109","author":[{"given":"Bidisha","family":"Sharma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chitralekha","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"358","article-title":"Bootstrapping a system for phoneme recognition and keyword spotting in unaccompanied singing","author":"kruspe","year":"2016","journal-title":"The International Society for Music Information Retrieval (ISMIR)"},{"key":"ref11","first-page":"281","article-title":"Modeling of phoneme durations for alignment between polyphonic audio and lyrics","author":"dzhambazov","year":"2015","journal-title":"Sound and Music Computing Conference"},{"key":"ref12","year":"0","journal-title":"Mirex 2018"},{"key":"ref13","article-title":"Mirex2018: Lyrics-to-audio alignment for instrument accompanied singings","author":"wang","year":"2018","journal-title":"Mirex 2018"},{"key":"ref14","first-page":"494","article-title":"Recognition of phonemes in a-cappella recordings using temporal patterns and mel frequency cepstral coefficients","author":"hansen","year":"2012","journal-title":"9th Sound and Music Computing Conference (SMC)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1267"},{"key":"ref16","article-title":"Harmonic\/percussive separation using median filtering","author":"fitzgerald","year":"2010","journal-title":"3th International Conference on Digital Audio Effects (DAFX10) Graz Austria"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1007\/978-3-319-53547-0_25","article-title":"Monoaural audio source separation using deep convolutional neural networks","author":"chandna","year":"2017","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"},{"key":"ref19","article-title":"Singing voice separation with deep U-Net convolutional networks","author":"jansson","year":"2017","journal-title":"The International Society for Music Information Retrieval (ISMIR)"},{"key":"ref28","year":"0","journal-title":"Good ASR result bad alignment result (lstm and dnn)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2006.38"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2159595"},{"key":"ref27","year":"0","journal-title":"nnet3 alignment issues"},{"key":"ref6","first-page":"3117","article-title":"Lever-aging repetition for improved automatic lyric transcription in popular music","author":"mcvicar","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref29","year":"0","journal-title":"Montreal forced aligner"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159577"},{"key":"ref8","article-title":"Semi-supervised lyrics and solo-singing alignment","author":"gupta","year":"2018","journal-title":"The International Society for Music Information Retrieval (ISMIR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2010-546047"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027576"},{"key":"ref1","first-page":"395","article-title":"Segmentation-based lyrics-audio alignment using dynamic programming","author":"lee","year":"2008","journal-title":"The International Society for Music Information Retrieval (ISMIR)"},{"key":"ref9","author":"sing!","year":"2010","journal-title":"Smule digital archive mobile performances(damp)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref22","article-title":"Knowledge-based Probabilistic Modeling for Tracking Lyrics in Music Audio Signals","author":"dzhambazov","year":"2017","journal-title":"Ph D thesis"},{"key":"ref21","year":"0","journal-title":"A chainer implementation of u-net singing voice separation model"},{"key":"ref24","first-page":"epfl-conf-192584","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding IEEE Signal Processing Society"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref25","year":"0","journal-title":"MIREX 2017"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682582.pdf?arnumber=8682582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:13:46Z","timestamp":1657854826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682582","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}