{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:22Z","timestamp":1774419502390,"version":"3.50.1"},"reference-count":28,"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\/icassp49660.2025.10890531","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["MathReader : Text-to-Speech for Mathematical Documents"],"prefix":"10.1109","author":[{"given":"Sieun","family":"Hyeon","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyudan","family":"Jung","sequence":"additional","affiliation":[{"name":"Chung-Ang University,Department of Mathematics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nam-Joon","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Gon","family":"Ryu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaeyoung","family":"Do","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Pdf reader in microsoft edge","year":"2024"},{"key":"ref2","volume-title":"Conveniently hear pdf files read aloud","year":"2024"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref5","first-page":"27980","article-title":"High-fidelity audio compression with improved rvqgan","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Kumar","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-534"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref8","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3395027.3419580"},{"key":"ref10","author":"Blecher","year":"2023","journal-title":"Nougat: Neural optical understanding for academic documents"},{"key":"ref11","article-title":"Upocr: Towards unified pixel-level ocr interface","volume-title":"Forty-first International Conference on Machine Learning","author":"Peng"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/app132212503"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI46756.2018.00069"},{"key":"ref14","author":"Raffel","year":"2023","journal-title":"Exploring the limits of transfer learning with a unified text-to-text transformer"},{"key":"ref15","first-page":"1","article-title":"Latexvoice: Application based on latex to generate documents designed for visually impaired users","volume":"2","author":"Sanmiguel","year":"2015","journal-title":"International Journal of Artificial Intelligence-IJAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300734"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3417009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888244"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.47397\/tb\/44-3\/tb138kortemeyer-accessibility"},{"key":"ref20","article-title":"Latex-gcl: Large language models (llms)-based data augmentation for text-attributed graph contrastive learning","author":"Yang","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPC.2021.3090722"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34595"},{"key":"ref23","volume-title":"Microsoft speech platform","year":"2024"},{"key":"ref24","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","article-title":"Mathbridge: A large corpus dataset for translating spoken mathematical expressions into latex formulas for improved readability","author":"Jung","year":"2024"},{"key":"ref28","volume-title":"Naver clovanote","year":"2024"}],"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\/10890531.pdf?arnumber=10890531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:11Z","timestamp":1774416191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890531","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}