{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:27:25Z","timestamp":1776889645653,"version":"3.51.2"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889081","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Evaluating the Impact of Discriminative and Generative E2E Speech Enhancement Models on Syllable Stress Preservation"],"prefix":"10.1109","author":[{"given":"Rangavajjala Sankara","family":"Bharadwaj","sequence":"first","affiliation":[{"name":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jhansi","family":"Mallela","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai Harshitha","family":"Aluru","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiranjeevi","family":"Yarra","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198236320.001.0001","volume-title":"Computer-assisted language learning: Context and conceptualization","author":"Levy","year":"1997"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.02.002"},{"key":"ref3","volume-title":"Speech enhancement","author":"Benesty","year":"2006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1811"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415269"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-015-9299-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP45357.2019.8969232"},{"key":"ref11","article-title":"An end-to-end approach for lexical stress detection based on transformer","author":"Ruan","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48312-7_26"},{"key":"ref13","first-page":"957","article-title":"The ISLE corpus of non-native spoken English","volume-title":"Proceedings of LREC: Language Resources and Evaluation Conference","volume":"2","author":"Menzel"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953277"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2019-15"},{"key":"ref16","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747417"},{"key":"ref19","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/NCC60321.2024.10486028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2290"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2631"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref30","article-title":"Music source separation in the waveform domain","author":"D\u00e9fossez","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref32","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"Valentini-Botinhao","year":"2017","journal-title":"University of Edinburgh. School of Informatics. Centre for Speech Technology Research (CSTR)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref34","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889081.pdf?arnumber=10889081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:06Z","timestamp":1774416366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889081","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}