{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:29:15Z","timestamp":1776356955526,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,4]]},"DOI":"10.1145\/3793853.3799808","type":"proceedings-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T14:25:49Z","timestamp":1775485549000},"page":"416-422","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Calliope: A TTS-based Narrated E-book Creator Ensuring Exact Synchronization, Privacy, and Layout Fidelity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9429-7148","authenticated-orcid":false,"given":"Hugo L.","family":"Hammer","sequence":"first","affiliation":[{"name":"Oslo Metropolitan University, Oslo, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6026-0929","authenticated-orcid":false,"given":"Vajira","family":"Thambawita","sequence":"additional","affiliation":[{"name":"Simula Research Laboratory, Oslo, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2073-7029","authenticated-orcid":false,"given":"P\u00e5l","family":"Halvorsen","sequence":"additional","affiliation":[{"name":"Simula Research Laboratory & University of Oslo, Oslo, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"aedocw. 2024. epub2tts: Turn an epub or text file into an audiobook. https:\/\/github.com\/aedocw\/epub2tts. GitHub Repository."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Edresson Casanova Kelly Davis Eren G\u00f6lge G\u00f6rkem G\u00f6knar Iulian Gulea Logan Hart Aya Aljafari Joshua Meyer Reuben Morais Samuel Olayemi et al. 2024. Xtts: a massively multilingual zero-shot text-to-speech model. arXiv preprint arXiv:2406.04904 (2024).","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"e_1_3_2_1_3_1","volume-title":"AVSP","volume":"2003","author":"Conrey Brianna L","year":"2003","unstructured":"Brianna L Conrey and David B Pisoni. 2003. Audiovisual asynchrony detection for speech and nonspeech signals. In AVSP, Vol. 2003. 25\u201330."},{"key":"e_1_3_2_1_4_1","unstructured":"DAISY Consortium. 2025. DAISY Standard Overview. https:\/\/daisy.org\/activities\/standards\/daisy\/."},{"key":"e_1_3_2_1_5_1","unstructured":"EDRLab. 2025. Thorium Reader. https:\/\/www.edrlab.org\/software\/thorium-reader\/."},{"key":"e_1_3_2_1_6_1","unstructured":"ElevenLabs. 2025. ElevenReader Official Website. https:\/\/elevenreader.io\/."},{"key":"e_1_3_2_1_7_1","unstructured":"Funway. 2025. audible-epub3-maker: Generate audiobooks from plain EPUB files. https:\/\/github.com\/funway\/audible-epub3-maker. GitHub Repository."},{"key":"e_1_3_2_1_8_1","first-page":"132","article-title":"Speech intelligibility derived from asynchronous processing of auditory-visual information","volume":"200","author":"Grant Ken W","year":"2001","unstructured":"Ken W Grant and Steven Greenberg. 2001. Speech intelligibility derived from asynchronous processing of auditory-visual information. In AVSP, Vol. 200. 132\u2013137.","journal-title":"AVSP"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1515\/iral-2023-0232"},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Machine Learning. PMLR, 5530\u20135540","author":"Kim Jaehyeon","year":"2021","unstructured":"Jaehyeon Kim, Jungil Kong, and Juhee Son. 2021. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In International Conference on Machine Learning. PMLR, 5530\u20135540."},{"key":"e_1_3_2_1_11_1","volume-title":"Flow Matching for Generative Modeling. In 11th International Conference on Learning Representations, ICLR","author":"Lipman Yaron","year":"2023","unstructured":"Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matt Le. 2023. Flow Matching for Generative Modeling. In 11th International Conference on Learning Representations, ICLR 2023."},{"key":"e_1_3_2_1_12_1","unstructured":"Mozilla Developer Network. 2025. Web Speech API Documentation. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Web_Speech_API\/Using_the_Web_Speech_API."},{"key":"e_1_3_2_1_13_1","unstructured":"NaturalSoft Ltd. 2025. NaturalReader Official Website. https:\/\/www.naturalreaders.com\/."},{"key":"e_1_3_2_1_14_1","volume-title":"Updated","author":"Henry O.","year":"2005","unstructured":"O. Henry. 2005. The Gift of the Magi. Project Gutenberg. https:\/\/www.gutenberg.org\/ebooks\/7256 eBook #7256. Updated: Dec 24, 2021."},{"key":"e_1_3_2_1_15_1","unstructured":"Alberto Pettarin. 2016. aeneas: A Python\/C library and set of tools to synchronize audio and text. https:\/\/github.com\/readbeyond\/aeneas."},{"key":"e_1_3_2_1_16_1","unstructured":"r4victor. 2024. syncabook: A tool for creating ebooks with synchronized text and audio. https:\/\/github.com\/r4victor\/syncabook. GitHub Repository."},{"key":"e_1_3_2_1_17_1","volume-title":"Afaligner: A tool for forced alignment.https:\/\/github.com\/r4victor\/afaligner\/.","year":"2025","unstructured":"r4victor. 2025. Afaligner: A tool for forced alignment.https:\/\/github.com\/r4victor\/afaligner\/."},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PMLR, 28492\u201328518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International conference on machine learning. PMLR, 28492\u201328518."},{"key":"e_1_3_2_1_19_1","unstructured":"Resemble AI. 2025. Chatterbox-TTS. https:\/\/github.com\/resemble-ai\/chatterbox. GitHub repository."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"e_1_3_2_1_21_1","volume-title":"Storyteller: Self-hosted platform for syncing audiobooks and ebooks. https:\/\/gitlab.com\/storyteller-platform\/storyteller. GitLab Repository.","year":"2025","unstructured":"Smoores. 2025. Storyteller: Self-hosted platform for syncing audiobooks and ebooks. https:\/\/gitlab.com\/storyteller-platform\/storyteller. GitLab Repository."},{"key":"e_1_3_2_1_22_1","unstructured":"World Wide Web Consortium. 2025. EPUB 3.3 Specification. https:\/\/www.w3.org\/TR\/epub-33\/."}],"event":{"name":"MMSys '26: ACM Multimedia Systems Conference 2026","location":"Hong Kong Hong Kong","acronym":"MMSys '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the ACM Multimedia Systems Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793853.3799808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:22:11Z","timestamp":1776352931000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793853.3799808"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":22,"alternative-id":["10.1145\/3793853.3799808","10.1145\/3793853"],"URL":"https:\/\/doi.org\/10.1145\/3793853.3799808","relation":{},"subject":[],"published":{"date-parts":[[2026,4,4]]},"assertion":[{"value":"2026-04-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}