{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T19:01:29Z","timestamp":1773514889999,"version":"3.50.1"},"reference-count":25,"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\/icassp49357.2023.10094916","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":1,"title":["F0 Estimation From Telephone Speech Using Deep Feature Loss"],"prefix":"10.1109","author":[{"given":"Supritha M","family":"Shetty","sequence":"first","affiliation":[{"name":"IIIT Dharwad,Electronics and Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shraddha","family":"Revankar","sequence":"additional","affiliation":[{"name":"KLE Technological University,School of Electronics and Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nalini C","family":"Iyer","sequence":"additional","affiliation":[{"name":"KLE Technological University,School of Electronics and Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K T","family":"Deepak","sequence":"additional","affiliation":[{"name":"IIIT Dharwad,Electronics and Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853845"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1972.1162410"},{"key":"ref14","article-title":"Robust f0 estimation of telephony speech using artificial neural networks","author":"virtanen","year":"2020","journal-title":"MSc Thesis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471741"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005751"},{"key":"ref2","article-title":"The role of fundamental frequency and formants in voice gender identification","volume":"18","author":"poon","year":"2014","journal-title":"Speech Language and Hearing Research"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.04.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-519"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2012194"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2018.01.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2495"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2009-6","article-title":"Multilingual mary tts participation in the blizzard challenge 2009","author":"schr\u00f6der","year":"2009","journal-title":"The Blizzard Challenge"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1109\/TASLP.2019.2942140","article-title":"Adversarial approximate inference for speech to electroglottograph conversion","volume":"27","author":"prathosh","year":"2019","journal-title":"IEEE\/ACM Trans Audio Speech and Language Processing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SPCOM55316.2022.9840808"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683298"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref7","article-title":"A robust algorithm for pitch tracking (rapt)","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.2951592"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON52576.2021.9691652"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(00)80024-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.759042"},{"key":"ref5","article-title":"Efficient algorithms for speech pitch estimation","author":"mei","year":"2001","journal-title":"Proceedings of 2001 International Symposium on Intelligent Multimedia Video and Speech Processing"}],"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\/10094916.pdf?arnumber=10094916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:08:58Z","timestamp":1729375738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094916","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}