{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:34:34Z","timestamp":1776890074261,"version":"3.51.2"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000055","name":"National Institute on Deafness and Other Communication Disorders","doi-asserted-by":"publisher","award":["R01DC012048"],"award-info":[{"award-number":["R01DC012048"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017186","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3313427","type":"journal-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T17:41:51Z","timestamp":1694626911000},"page":"3760-3770","source":"Crossref","is-referenced-by-count":5,"title":["$F0$ Estimation and Voicing Detection With Cascade Architecture in Noisy Speech"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1343-2713","authenticated-orcid":false,"given":"Yixuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3057-9060","authenticated-orcid":false,"given":"Heming","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8195-6319","authenticated-orcid":false,"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, Ohio State University, Columbus, OH, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref2","article-title":"A robust algorithm for pitch tracking (RAPT)","volume":"495","author":"Talkin","year":"1995","journal-title":"Speech Coding Synth."},{"key":"ref3","first-page":"97","article-title":"Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound","volume-title":"Proc. Conf. Inst. Phonetic Sci.","volume":"17","author":"Boersma","year":"1993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2168518"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2295918"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tsa.2003.811539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2077280"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2363410"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2815"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414050"},{"key":"ref12","article-title":"Cross-domain neural pitch and periodicity estimation","author":"Morrison","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.2939132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-633"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11156"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082318"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138716"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053460"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902550"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref24","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1073"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461526"},{"key":"ref28","article-title":"Pitch of voiced speech in the short-time Fourier transform: Algorithms, ground truths, and evaluation methods","author":"Bechtold","year":"2021"},{"key":"ref29","article-title":"An analysis\/synthesis framework for automatic F0 annotation of multitrack datasets","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Salamon","year":"2017"},{"key":"ref30","article-title":"Synthesis and expressive transformation of singing voice","author":"Ardaillon","year":"2017"},{"key":"ref31","first-page":"1","article-title":"A four-parameter model of glottal flow","volume":"26","author":"Fant","year":"1985","journal-title":"STL-QPSR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref33","first-page":"71","article-title":"Fast and reliable F0 estimation method based on the period extraction of vocal fold vibration of singing voice and speech","volume-title":"Proc. 35th Int. Conf. Audio Eng. Soc.","author":"Morise","year":"2009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1250\/ast.33.123"},{"key":"ref36","article-title":"Torchcrepe","author":"Morrison","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1993-241"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414929"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414398"},{"key":"ref46","article-title":"Investigating U-Nets with various intermediate blocks for spectrogram-based singing voice separation","volume-title":"Proc. 21st Int. Soc. Music Inf. Retrieval Conf.","author":"Choi","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10162-008-0143-x"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/9970249\/10250914-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10250914.pdf?arnumber=10250914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T03:26:31Z","timestamp":1705029991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10250914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3313427","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}