{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:22:06Z","timestamp":1764400926172,"version":"3.46.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249184","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"944-949","source":"Crossref","is-referenced-by-count":0,"title":["LAPS-Diff: A Diffusion-Based Framework for Hindi Singing Voice Synthesis with Language Aware Prosody-Style Guided Learning"],"prefix":"10.1109","author":[{"given":"Sandipan","family":"Dhar","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Bombay,Department of Electrical Engineering,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayank","family":"Gupta","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay,Department of Electrical Engineering,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Preeti","family":"Rao","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay,Department of Electrical Engineering,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-678"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106762"},{"key":"ref5","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-33"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.693"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-444"},{"key":"ref11","article-title":"Styletts 2: Towards human-level text-tospeech through style diffusion and adversarial training with large speech language models","volume":"36","author":"Li","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/app9071324"},{"key":"ref13","article-title":"MERT: Acoustic music understanding model with large-scale self-supervised training","volume-title":"The Twelfth International Conference on Learning Representations","author":"LI","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21327"},{"volume-title":"G. Lab, Gaudio studio: Ai-powered audio processing","year":"2024","key":"ref15"},{"key":"ref16","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding, IEEE Signal Processing Society","author":"Povey","year":"2011"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"North American Chapter of the Association for Computational Linguistics"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3530171"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1896\/1\/012004"},{"volume-title":"Diffsinger: Singing voice synthesis via shallow diffusion mechanism","year":"2021","author":"Liu","key":"ref20"},{"volume-title":"D. o. C. S IIT Madras and Engineering, Indictts common label set","year":"2020","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037956"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2014.6830601"},{"key":"ref25","volume":"abs\/2502.05139","author":"Tjandra","year":"2025","journal-title":"Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249184.pdf?arnumber=11249184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:20:21Z","timestamp":1764400821000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249184","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}