{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T08:16:27Z","timestamp":1771488987828,"version":"3.50.1"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"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":[[2025,11,12]]},"DOI":"10.1109\/o-cocosda68185.2025.11385168","type":"proceedings-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:14:09Z","timestamp":1771449249000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Accent Conversion: Preserving Speaker Identity in Native English Synthesis"],"prefix":"10.1109","author":[{"given":"Sabyasachi","family":"Chandra","sequence":"first","affiliation":[{"name":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puja","family":"Bharati","sequence":"additional","affiliation":[{"name":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Debolina","family":"Pramanik","sequence":"additional","affiliation":[{"name":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shyamal Kumar","family":"Das Mandal","sequence":"additional","affiliation":[{"name":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riya","family":"Sil","sequence":"additional","affiliation":[{"name":"Brainware University,Department of Computer Science & Engineering,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-2004"},{"key":"ref2","first-page":"2013","author":"Aryal","year":"2013","journal-title":"Foreign accent conversion through voice morphing"},{"key":"ref3","author":"Baevski","year":"2020","journal-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"101302","DOI":"10.1016\/j.csl.2021.101302","article-title":"2021. Accentron: Foreign accent conversion to arbitrary non-native speakers using zero-shot learning","volume":"72","author":"Ding","year":"2021","journal-title":"Comput. Speech Lang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2009.2038818"},{"key":"ref6","article-title":"2014. Deep Speech: Scaling up end-to-end speech recognition","author":"Hannun","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.03385"},{"key":"ref8","article-title":"2021. HuBERT: Self- Supervised Speech Representation Learning by Masked Prediction of Hidden Units","author":"Hsu","journal-title":"arXiv"},{"key":"ref9","first-page":"64","article-title":"2007. Spoken language conversion with accent morphing","volume-title":"In Proc. 6th ISCA Workshop on Speech Synthesis (SSW 6)","author":"Huckvale"},{"key":"ref10","article-title":"2019. Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","volume-title":"arXiv","author":"Jia"},{"key":"ref11","article-title":"2022. FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion","author":"li","journal-title":"arXiv"},{"key":"ref12","article-title":"2018. Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","volume-title":"arXiv","author":"Shen"},{"issue":"86","key":"ref13","first-page":"2579","article-title":"2008. Visualizing Data using t- SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"2020. Generalized End-to-End Loss for Speaker Verification","author":"Wan","journal-title":"arXiv"},{"key":"ref15","article-title":"2019. CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR","volume-title":"Voice Cloning Toolkit (version 0.92).","author":"Yamagishi"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2019.2960721"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"}],"event":{"name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Yogyakarta, Indonesia","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,14]]}},"container-title":["2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11383559\/11384821\/11385168.pdf?arnumber=11385168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T07:14:38Z","timestamp":1771485278000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11385168\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda68185.2025.11385168","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}