{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T04:32:28Z","timestamp":1770352348248,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["309629"],"award-info":[{"award-number":["309629"]}],"id":[{"id":"10.13039\/501100002341","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":[[2019,12]]},"DOI":"10.1109\/taslp.2019.2945489","type":"journal-article","created":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T20:03:16Z","timestamp":1570219396000},"page":"2336-2349","source":"Crossref","is-referenced-by-count":8,"title":["Statistical Regression Models for Noise Robust F0 Estimation Using Recurrent Deep Neural Networks"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5796-2310","authenticated-orcid":false,"given":"Akihiro","family":"Kato","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4371-7322","authenticated-orcid":false,"given":"Tomi H.","family":"Kinnunen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162846"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811539"},{"key":"ref37","first-page":"799","article-title":"Bidirectional LSTM networks for improved phoneme classification and recognition","author":"graves","year":"0","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref36","first-page":"193","article-title":"Applying LSTM to time series predictable through time-window approaches","author":"gers","year":"0","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref34","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"0","journal-title":"NIPS 2014 Deep Learning Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref40","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref12","first-page":"2258","article-title":"F0 estimation in noisy speech based on long-term harmonic feature analysis combined with neural network classification","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2295918"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876880"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2077280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.07.005"},{"key":"ref4","article-title":"Systems, methods, and apparatus for signal encoding using pitch-regularizing and non-pitch-regularizing coding","author":"rajendran","year":"2017"},{"key":"ref27","first-page":"61","article-title":"Overview of the 2000-2001 ELISA consortium research activities","author":"magrin-chagnolleau","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1585"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-928"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1973.9030"},{"key":"ref5","first-page":"2695","article-title":"Using hidden Markov models for speech enhancement","author":"kato","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.05.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-537"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref9","first-page":"495","article-title":"A robulst algorithm for pitch tracking (RAPT)","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-246"},{"key":"ref46","first-page":"1509","article-title":"A pitch tracking corpus with evaluation on multipitch tracking scenario","author":"pirker","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2363410"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J Royal Statist Soc Series B (Methodol )"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-679"},{"key":"ref47","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2667879"},{"key":"ref42","volume":"3","author":"duda","year":"1973","journal-title":"Pattern Classification and Scene Analysis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1671"},{"key":"ref41","first-page":"318","article-title":"Learning internal representations by error propagation","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructures of Cognition"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828650"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683379"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2076805"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74200-5_19"},{"key":"ref25","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"2017","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8817316\/08859278.pdf?arnumber=8859278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T15:49:04Z","timestamp":1721836144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8859278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":47,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2945489","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}