{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:24Z","timestamp":1765008864312,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","funder":[{"name":"the RGC of the HKSAR, China","award":["UGC\/FDS16\/E13\/23"],"award-info":[{"award-number":["UGC\/FDS16\/E13\/23"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3771030","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SynSpeech: A Dataset and Benchmark for Fake Speech Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0776-7456","authenticated-orcid":false,"given":"Qifeng","family":"Qiu","sequence":"first","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3142-6397","authenticated-orcid":false,"given":"Yutian","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9619-6041","authenticated-orcid":false,"given":"Lap-Kei","family":"Lee","sequence":"additional","affiliation":[{"name":"Hong Kong Metropolitan University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3976-0053","authenticated-orcid":false,"given":"Fu Lee","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong Metropolitan University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9392-1375","authenticated-orcid":false,"given":"Zhenguo","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Max Bain Jaesung Huh Tengda Han and Andrew Zisserman. 2023. WhisperX: Time-Accurate Speech Transcription of Long-Form Audio. INTERSPEECH (2023).","DOI":"10.21437\/Interspeech.2023-78"},{"key":"e_1_3_3_2_3_2","volume-title":"NeurIPS","author":"Frank Joel","year":"2021","unstructured":"Joel Frank and Lea Sch\u00f6nherr. 2021. WaveFake: A Data Set to Facilitate Audio Deepfake Detection. In NeurIPS."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00395"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"key":"e_1_3_3_2_7_2","first-page":"413","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024","author":"Ji Zhoulin","year":"2024","unstructured":"Zhoulin Ji, Chenhao Lin, Hang Wang, and Chao Shen. 2024. Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024. ijcai.org, 413\u2013421."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"e_1_3_3_2_9_2","first-page":"1496","volume-title":"INTERSPEECH","author":"Jung Jee-weon","year":"2020","unstructured":"Jee-weon Jung, Seung-bin Kim, et\u00a0al. 2020. Improved RawNet with Feature Map Scaling for Text-Independent Speaker Verification Using Raw Waveforms. In INTERSPEECH. 1496\u20131500."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"e_1_3_3_2_11_2","volume-title":"NeurIPS","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. In NeurIPS."},{"key":"e_1_3_3_2_12_2","first-page":"5530","volume-title":"ICML","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 ICML. 5530\u20135540."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"e_1_3_3_2_14_2","volume-title":"NeurIPS","author":"Kong Jungil","year":"2020","unstructured":"Jungil Kong, Jaehyeon Kim, and Jaekyoung Bae. 2020. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. In NeurIPS."},{"key":"e_1_3_3_2_15_2","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Kong Zhifeng","year":"2021","unstructured":"Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, and Bryan Catanzaro. 2021. DiffWave: A Versatile Diffusion Model for Audio Synthesis. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.6203248"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670285"},{"key":"e_1_3_3_2_18_2","volume-title":"NeurIPS","author":"Li Yinghao\u00a0Aaron","year":"2023","unstructured":"Yinghao\u00a0Aaron Li, Cong Han, Vinay\u00a0S. Raghavan, Gavin Mischler, and Nima Mesgarani. 2023. StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models. In NeurIPS."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Haoxin Ma Jiangyan Yi Chenglong Wang Xinrui Yan Jianhua Tao Tao Wang Shiming Wang and Ruibo Fu. 2024. CFAD: A Chinese dataset for fake audio detection. Speech Commun. 164 (2024) 103122.","DOI":"10.1016\/j.specom.2024.103122"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650962"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Hyung-Seok Oh Sang-Hoon Lee and Seong-Whan Lee. 2024. DiffProsody: Diffusion-Based Latent Prosody Generation for Expressive Speech Synthesis With Prosody Conditional Adversarial Training. IEEE ACM Trans. Audio Speech Lang. Process. (2024) 2654\u20132666.","DOI":"10.1109\/TASLP.2024.3395994"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906599"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_3_2_26_2","first-page":"1008","volume-title":"INTERSPEECH","author":"Todisco Massimiliano","year":"2019","unstructured":"Massimiliano Todisco, Xin Wang, Ville Vestman, Md. Sahidullah, et\u00a0al. 2019. ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection. In INTERSPEECH. 1008\u20131012."},{"key":"e_1_3_3_2_27_2","first-page":"1344","volume-title":"INTERSPEECH","author":"Wang Disong","year":"2021","unstructured":"Disong Wang, Liqun Deng, Yu\u00a0Ting Yeung, Xiao Chen, Xunying Liu, and Helen Meng. 2021. VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-Shot Voice Conversion. In INTERSPEECH. 1344\u20131348."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Xiang Wu Ran He Zhenan Sun and Tieniu Tan. 2018. A Light CNN for Deep Face Representation With Noisy Labels. IEEE Trans. Inf. Forensics Secur. (2018) 2884\u20132896.","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"e_1_3_3_2_29_2","first-page":"2037","volume-title":"INTERSPEECH","author":"Wu Zhizheng","year":"2015","unstructured":"Zhizheng Wu, Tomi Kinnunen, Nicholas W.\u00a0D. Evans, et\u00a0al. 2015. ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge. In INTERSPEECH. 2037\u20132041."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Junichi Yamagishi Christophe Veaux and Kirsten MacDonald. 2019. CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92). 10.7488\/ds\/2645","DOI":"10.7488\/ds\/2645"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Dongchao Yang Jianwei Yu Helin Wang Wen Wang Chao Weng Yuexian Zou and Dong Yu. 2023. Diffsound: Discrete Diffusion Model for Text-to-Sound Generation. IEEE ACM Trans. Audio Speech Lang. Process. 31 (2023) 1720\u20131733.","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687845"},{"key":"e_1_3_3_2_33_2","first-page":"1654","volume-title":"INTERSPEECH","author":"Yi Jiangyan","year":"2021","unstructured":"Jiangyan Yi, Ye Bai, Jianhua Tao, et\u00a0al. 2021. Half-Truth: A Partially Fake Audio Detection Dataset. In INTERSPEECH. 1654\u20131658."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"e_1_3_3_2_35_2","first-page":"1073","volume-title":"INTERSPEECH","author":"Zeinali Hossein","year":"2019","unstructured":"Hossein Zeinali, Themos Stafylakis, Georgia Athanasopoulou, Johan Rohdin, Ioannis Gkinis, Luk\u00e1s Burget, and Jan Cernock\u00fd. 2019. Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge. In INTERSPEECH. 1073\u20131077."},{"key":"e_1_3_3_2_36_2","first-page":"117","volume-title":"IWDW","author":"Zhang Zhenyu","year":"2021","unstructured":"Zhenyu Zhang, Yewei Gu, Xiaowei Yi, and Xianfeng Zhao. 2021. FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection. In IWDW. 117\u2013131."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688322"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3771030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:10:33Z","timestamp":1765008633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3771030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":36,"alternative-id":["10.1145\/3743093.3771030","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3771030","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}