{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:50Z","timestamp":1774420070215,"version":"3.50.1"},"reference-count":7,"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\/icassp49660.2025.10887580","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-2","source":"Crossref","is-referenced-by-count":1,"title":["HamaraAwaz: Advancing Low-Latency Streaming TTS for Multilingual Speech in Indian Languages"],"prefix":"10.1109","author":[{"given":"Neil","family":"Shah","sequence":"first","affiliation":[{"name":"IIIT Hyderabad,CVIT,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parth","family":"Khadse","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shirish","family":"Karande","sequence":"additional","affiliation":[{"name":"TCS Research,Pune,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunil Kumar","family":"Kopparapu","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"79","article-title":"Parrottts: Text-to-speech synthesis exploiting disentangled self-supervised representations","volume-title":"Findings of the Association for Computational Linguistics: EACL 2024","author":"Shah"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref3","first-page":"860","article-title":"Textless speech-to-speech translation on real data","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Lee"},{"key":"ref4","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref6","article-title":"Deepforcedaligner","author":"Ideas"},{"key":"ref7","article-title":"LIMMITS\u201925 Challenge - Low-latency, Multilingual, Multi-Speaker Text-to-Speech"}],"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\/10887580.pdf?arnumber=10887580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:14Z","timestamp":1774416374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":7,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887580","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}