{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T10:13:43Z","timestamp":1758190423657,"version":"3.44.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"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":[[2025,8,3]]},"DOI":"10.1109\/ialp68296.2024.11156270","type":"proceedings-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:32:18Z","timestamp":1758043938000},"page":"123-128","source":"Crossref","is-referenced-by-count":0,"title":["Whether to Use Pretrain Neural Vocoders or Not?: An Empirical Analysis for Indic Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ravindrakumar M.","family":"Purohit","sequence":"first","affiliation":[{"name":"Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[{"name":"Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/600167"},{"volume-title":"Glottolog","year":"2024","author":"Hammarstr\u00f6m","key":"ref2"},{"key":"ref3","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1250\/ast.27.349"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1976.1169987"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00274-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2786"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref13","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems (NIPS)","volume":"33","author":"Kong","year":"2020"},{"key":"ref14","article-title":"BigVGAN: A universal neural vocoder with large-scale training","author":"Lee","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv preprint arXiv"},{"volume-title":"SYSPIN S1.0 Corpus - A TTS Corpus of 900+ hours in nine Indian Languages","year":"2025","key":"ref16"},{"key":"ref17","article-title":"IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS","volume-title":"NeurIPS Datasets and Benchmarks","author":"Sankar","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"volume-title":"The LJ Speech Dataset","year":"2024","author":"Ito","key":"ref22"},{"volume-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"volume-title":"ludlows\/python-pesq: supporting for multiprocessing features","year":"2022","author":"Wang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746398"}],"event":{"name":"2025 International Conference on Asian Language Processing (IALP)","start":{"date-parts":[[2025,8,3]]},"location":"Sarawak, Malaysia","end":{"date-parts":[[2025,8,6]]}},"container-title":["2025 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11156192\/11156242\/11156270.pdf?arnumber=11156270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T05:18:17Z","timestamp":1758086297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11156270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ialp68296.2024.11156270","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]}}}