{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:55:42Z","timestamp":1759938942315,"version":"3.33.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832229","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"929-936","source":"Crossref","is-referenced-by-count":1,"title":["SPMIS: An Investigation of Synthetic Spoken Misinformation Detection"],"prefix":"10.1109","author":[{"given":"Peizhuo","family":"Liu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renqiang","family":"He","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haorui","family":"He","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei International Pte Ltd,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huadi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Shi","sequence":"additional","affiliation":[{"name":"Huawei International Pte Ltd,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Northeastern University,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000127"},{"key":"ref2","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023","journal-title":"arXiv preprint arXiv:2305.09636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref4","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint arXiv:2403.03100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832255"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832365"},{"issue":"4","key":"ref7","first-page":"86","article-title":"Speech recognition and synthesis tool: Assistive technology for physically disabled persons","volume":"3","author":"Reena Sharma","year":"2012","journal-title":"International Journal of Computer Science and Telecommunications"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645385"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2671435"},{"key":"ref12","article-title":"Audio deepfake detection: A survey","author":"Yi","year":"2023","journal-title":"arXiv preprint arXiv:2308.14970"},{"key":"ref13","article-title":"Audio anti-spoofing detection: A survey","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2404.13914"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref17","article-title":"Add 2023: The second audio deepfake detection challenge","author":"Yi","year":"2023","journal-title":"arXiv preprint arXiv:2305.13774"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446549"},{"key":"ref19","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume":"33","author":"Kiela","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23062"},{"key":"ref21","first-page":"6","article-title":"Evaluating unsupervised text classification: Zero-shot and similarity-based approaches","volume-title":"Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval","volume":"22","author":"Schopf"},{"article-title":"Hansard speeches 1979-2021: Version 3.1.0","year":"2021","author":"Odell","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nllp-1.20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.44"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref26","article-title":"Openvoice: Versatile instant voice cloning","author":"Qin","year":"2023","journal-title":"arXiv preprint arXiv:2312.01479"},{"key":"ref27","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. of ICML","author":"Radford"},{"key":"ref28","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref29","article-title":"Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks","author":"Jung","year":"2021","journal-title":"arXiv preprint arXiv:2110.01200"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref32","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. of NAACL","author":"Devlin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832229.pdf?arnumber=10832229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:19:02Z","timestamp":1737101942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832229","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}