{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:28:56Z","timestamp":1765499336773,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761492","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:59:18Z","timestamp":1762559958000},"page":"6668-6672","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Achoio: A Skill-Aware Evaluation Management System for Text-To-Speech Research"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1359-872X","authenticated-orcid":false,"given":"Haowei","family":"Lou","sequence":"first","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4425-7388","authenticated-orcid":false,"given":"Hye-Young","family":"Paik","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2674-0253","authenticated-orcid":false,"given":"Basem","family":"Suleiman","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4076-1811","authenticated-orcid":false,"given":"Wen","family":"Hu","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4149-839X","authenticated-orcid":false,"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, The University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"What Is Amazon Mechanical Turk? Amazon. com","author":"Services Amazon Web","year":"2025","unstructured":"Amazon Web Services. 2025. What Is Amazon Mechanical Turk? Amazon. com, Inc. https:\/\/docs.aws.amazon.com\/AWSMechTurk\/latest\/AWSMechanicalTurkRequester\/WhatIs.html Accessed 31 May 2025."},{"key":"e_1_3_2_1_2_1","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim Jaehyeon","year":"2020","unstructured":"Jaehyeon Kim, Sungwon Kim, Jungil Kong, and Sungroh Yoon. 2020. Glow-tts: A generative flow for text-to-speech via monotonic alignment search. Advances in Neural Information Processing Systems 33 (2020), 8067--8077.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696409.3700163"},{"key":"e_1_3_2_1_5_1","volume-title":"Generalized Multilingual Text-to-Speech Generation with Language-Aware Style Adaptation. arXiv preprint arXiv:2504.08274","author":"Lou Haowei","year":"2025","unstructured":"Haowei Lou, Hye-young Paik, Sheng Li,Wen Hu, and Lina Yao. 2025. Generalized Multilingual Text-to-Speech Generation with Language-Aware Style Adaptation. arXiv preprint arXiv:2504.08274 (2025)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_7_1","volume-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558","author":"Ren Yi","year":"2020","unstructured":"Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2020. Fastspeech 2: Fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Fastspeech: Fast, robust and controllable text to speech. Advances in neural information processing systems 32","author":"Ren Yi","year":"2019","unstructured":"Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019. Fastspeech: Fast, robust and controllable text to speech. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. PMLR, 1530--1538","author":"Rezende Danilo","year":"2015","unstructured":"Danilo Rezende and Shakir Mohamed. 2015. Variational inference with normalizing flows. In International conference on machine learning. PMLR, 1530--1538."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_12_1","volume-title":"Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135","author":"Wang Yuxuan","year":"2017","unstructured":"Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, et al. 2017. Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)."},{"key":"e_1_3_2_1_13_1","volume-title":"Frechet inception distance (fid) for evaluating gans","author":"Yu Yu","year":"2021","unstructured":"Yu Yu, Weibin Zhang, and Yun Deng. 2021. Frechet inception distance (fid) for evaluating gans. China University of Mining Technology Beijing Graduate School 3, 11 (2021)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:23:59Z","timestamp":1765499039000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761492"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":13,"alternative-id":["10.1145\/3746252.3761492","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761492","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}