{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:24:04Z","timestamp":1776885844157,"version":"3.51.2"},"reference-count":31,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414050","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"61-65","source":"Crossref","is-referenced-by-count":23,"title":["DeepF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals"],"prefix":"10.1109","author":[{"given":"Satwinder","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanhang","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1593"},{"key":"ref30","article-title":"mir eval: A transparent implementation of common MIR metrics","author":"raffel","year":"2014","journal-title":"15th International Society for Music Information Retrieval Conference"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2295918"},{"key":"ref11","article-title":"Yet Another Algorithm for Pitch Tracking:(YAAPT)","author":"kasi","year":"2002","journal-title":"Ph D thesis"},{"key":"ref12","first-page":"161","article-title":"CREPE: A convolutional representation for pitch estimation","author":"kim","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2363410"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2286"},{"key":"ref15","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"2015","journal-title":"Annual Conference of the International Speech Communication Association"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-679"},{"key":"ref17","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref18","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101029"},{"key":"ref27","first-page":"155","article-title":"Medleydb: A multitrack dataset for annotation-intensive mir research","volume":"14","author":"bittner","year":"2014","journal-title":"ISMIR"},{"key":"ref3","first-page":"2494","article-title":"A pitch extraction algorithm tuned for automatic speech recognition","author":"ghahremani","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","first-page":"518","article-title":"A robust algorithm for pitch tracking (RAPT)","volume":"495","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2042119"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app9071324"},{"key":"ref8","first-page":"659","article-title":"pYIN: A fundamental frequency estimator using probabilistic threshold distributions","author":"mauch","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2982285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.2951592"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11338"},{"key":"ref22","article-title":"An analysis\/synthesis framework for automatic f0 annotation of multi-track datasets","author":"salamon","year":"2017","journal-title":"18th International Society for Music Information Retrieval Conference"},{"key":"ref21","first-page":"310","article-title":"On the improvement of singing voice separation for monaural recordings using the MIR-1K dataset","volume":"18","author":"hsu","year":"2009","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref24","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"27th International Conference on Machine Learning"},{"key":"ref23","article-title":"A pitch tracking corpus with evaluation on multipitch tracking scenario","author":"pirker","year":"2011","journal-title":"Annual Conference of the International Speech Communication Association"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref25","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09414050.pdf?arnumber=9414050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:47Z","timestamp":1652182847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414050","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}