{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T18:21:42Z","timestamp":1775845302811,"version":"3.50.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389767","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["No Pitch Left Behind: Addressing Gender Unbalance In Automatic Speech Recognition Through Pitch Manipulation"],"prefix":"10.1109","author":[{"given":"Dennis","family":"Fucci","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Gaido","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Negri","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mauro","family":"Cettolo","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luisa","family":"Bentivogli","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1515\/9781474473330"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1746"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2993"},{"key":"ref4","article-title":"Quantifying Bias in Automatic Speech Recognition","author":"Feng","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1606"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3347449.3357480"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.gebnlp-1.10"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-699"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.226966"},{"issue":"10","key":"ref10","article-title":"Improving Speech Recognition Performance through Gender Separation","volume":"9","author":"Abdulla","year":"2001","journal-title":"Changes"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2018916200"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.05.002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-36"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2020.3045349"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref16","article-title":"Vocal Tract Length Perturbation (VTLP) Improves Speech Recognition","author":"Jaitly","year":"2013","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.08.002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053334"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1901.168"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3758\/APP.71.5.1150"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1168\/2\/022022"},{"key":"ref22","article-title":"Deep Speech: Scaling up End-to-End Speech Recognition","author":"Hannun","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372913"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003741"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-711"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1161"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-207"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3227"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414116"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.108643"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746281"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11343"},{"issue":"9\/10","key":"ref36","first-page":"341","article-title":"Praat, a System for Doing Phonetics by Computer","volume":"5","author":"Boersma","year":"2001","journal-title":"Glot International"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90021-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-827"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref44","first-page":"137","article-title":"On Target Segmentation for Direct Speech Translation","author":"Di Gangi","year":"2020","journal-title":"AMTA"},{"key":"ref45","first-page":"33","article-title":"Fairseq S2T: Fast Speech-to-Text Modeling with Fairseq","author":"Wang","year":"2020","journal-title":"AACLIJCNLP"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref47","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref49","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref51","article-title":"When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP","author":"Papi","year":"2023"},{"key":"ref52","first-page":"388","article-title":"Statistical Significance Tests for Machine Translation Evaluation","author":"Koehn","year":"2004","journal-title":"EMNLP"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.619"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389767.pdf?arnumber=10389767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:28Z","timestamp":1706027788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389767","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}