{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:27Z","timestamp":1764399087122,"version":"3.46.0"},"reference-count":34,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306029"],"award-info":[{"award-number":["62306029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L233032"],"award-info":[{"award-number":["L233032"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","award":["K00120240007"],"award-info":[{"award-number":["K00120240007"]}],"id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249147","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"771-776","source":"Crossref","is-referenced-by-count":0,"title":["I\n                    <sup>2<\/sup>\n                    TTS: Image-Indicated Immersive Text-to-Speech Synthesis with Spatial Perception"],"prefix":"10.1109","author":[{"given":"Jiawei","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology Beijing,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian-Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaran","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijie","family":"Tao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyuan","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu-Cheng","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. of Int. Conf. on Machine Learning","author":"Kim","year":"2021"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","first-page":"2709","article-title":"Yourtts: Towards zeroshot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"Proc. of Int. Conf. on Machine Learning","author":"Casanova","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29769"},{"issue":"4","key":"ref9","first-page":"249","article-title":"Comparison of different impulse response measurement techniques","volume":"50","author":"Stan","year":"2002","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10348"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.990"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888876"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. of Int. Conf. on Machine Learning","author":"Radford","year":"2021"},{"volume-title":"From text to speech: The MITalk system","year":"1987","author":"Allen","key":"ref15"},{"volume-title":"The festival speech synthesis system","year":"1998","author":"Black","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224415"},{"key":"ref18","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Diff-tts: A denoising diffusion model for text-tospeech","author":"Jeong","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref21","article-title":"Clam-tts: Improving neural codec language model for zero-shot text-to-speech","volume-title":"Proc. of Int. Conf. on Learning Representations","author":"Kim","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref23","article-title":"Naturalspeech3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00035"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref26","article-title":"Selfsupervised visual acoustic matching","volume":"36","author":"Somayazulu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"7748","article-title":"Metastylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"International Conference on Machine Learning","author":"Min","year":"2021"},{"key":"ref28","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"The lj speech dataset","year":"2017","author":"Ito","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref32","article-title":"Scglowtts: An efficient zero-shot multi-speaker text-tospeech model","author":"Casanova","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"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\/11249147.pdf?arnumber=11249147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:29Z","timestamp":1764399029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249147","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}