{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:09:38Z","timestamp":1781194178386,"version":"3.54.1"},"reference-count":58,"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"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832250","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"921-928","source":"Crossref","is-referenced-by-count":11,"title":["DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset"],"prefix":"10.1109","author":[{"given":"Jiawei","family":"Du","sequence":"first","affiliation":[{"name":"National Taiwan University,Department of Computer Science Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I-Ming","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I-Hsiang","family":"Chiu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Electrical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanjun","family":"Chen","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering,National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Wu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering,National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenze","family":"Ren","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering,National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering,National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2","article-title":"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative ai","volume":"2","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.13336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"key":"ref8","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","volume":"32","author":"Ren"},{"key":"ref9","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref10","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","volume":"33","author":"Kim"},{"key":"ref11","article-title":"Flow matching in latent space","author":"Dao","year":"2023","journal-title":"arXiv preprint arXiv:2307.08698"},{"key":"ref12","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv:2210.02747"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref14","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2023","journal-title":"arXiv preprint arXiv:2304.09116"},{"key":"ref15","article-title":"Styletts 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","volume-title":"Proc. NeurIPS","volume":"36","author":"Li"},{"key":"ref16","article-title":"Speechgpt-gen: Scaling chain-of-information speech generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2401.13527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref18","article-title":"Guided-tts: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref19","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv:2009.00713"},{"key":"ref20","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv preprint arXiv:2009.09761"},{"key":"ref21","article-title":"Bddm: Bilateral denoising diffusion models for fast and high-quality speech synthesis","author":"Lam","year":"2022","journal-title":"arXiv preprint arXiv:2203.13508"},{"key":"ref22","article-title":"Priorgrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","author":"Lee","year":"2021","journal-title":"arXiv preprint arXiv:2106.06406"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref25","article-title":"P-flow: A fast and data-efficient zero-shot TTS through speech prompting","author":"Kim","year":"2023","journal-title":"NeurIPS"},{"key":"ref26","article-title":"The defender\u2019s perspective on automatic speaker verification: An overview","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2305.12804"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2022-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1185"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1191"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1472"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447811"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3059479"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2093"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref37","article-title":"Wavefake: A data set to facilitate audio deepfake detection","author":"Frank","year":"2021","journal-title":"arXiv preprint arXiv:2111.02813"},{"key":"ref38","article-title":"Does audio deepfake detection generalize?","author":"Nicolas","year":"2022","journal-title":"arXiv preprint arXiv:2203.16263"},{"key":"ref39","article-title":"Mlaad: The multi-language audio anti-spoofing dataset","author":"Nicolas","year":"2024","journal-title":"arXiv preprint arXiv:2401.09512"},{"key":"ref40","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","volume-title":"Proc. CSTR","author":"Yamagishi"},{"key":"ref41","article-title":"Jsut corpus: free large-scale japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv preprint arXiv:1711.00354"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3276480"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ReTIS.2015.7232917"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"ref47","article-title":"Audio anti-spoofing detection: A survey","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2404.13914"},{"key":"ref48","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref49","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445948"},{"key":"ref51","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":"ref52","article-title":"CM-TTS: Enhancing real time text-tospeech synthesis efficiency through weighted samplers and consistency models","author":"Li","year":"2024","journal-title":"Findings of NAACL"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3395994"},{"key":"ref54","article-title":"Diffar: Denoising diffusion autoregressive model for raw speech waveform generation","author":"Benita","year":"2023","journal-title":"arXiv preprint arXiv:2310.01381"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2015.0094"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-479"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"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\/10832250.pdf?arnumber=10832250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:42:03Z","timestamp":1737099723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832250","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}