{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:27Z","timestamp":1774420047194,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890188","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["WaveSpect: A Hybrid Approach to Synthetic Audio Detection via Waveform and Spectrogram Analysis"],"prefix":"10.1109","author":[{"given":"Dong","family":"Chen","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science,Guangzhou,China"}]},{"given":"Fan","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science,Guangzhou,China"}]},{"given":"Zhengxuan","family":"Song","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science,Guangzhou,China"}]},{"given":"Wei","family":"Zhu","sequence":"additional","affiliation":[{"name":"China Mobile Internet Corporation China Mobile Communications Corporation,Guangzhou,China"}]},{"given":"Yin","family":"Yang","sequence":"additional","affiliation":[{"name":"China Mobile Internet Corporation China Mobile Communications Corporation,Guangzhou,China"}]},{"given":"Kun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3035416"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095927"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288895"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447701"},{"key":"ref11","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193459"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref17","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448336"},{"key":"ref20","article-title":"Openvoice: Versatile instant voice cloning","author":"Qin","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1698"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3431888"},{"key":"ref23","article-title":"Self-attention and hybrid features for replay and deep-fake audio detection","author":"Huang","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2024.103720"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2022-14"},{"key":"ref28","article-title":"Vision transformer for small-size datasets","author":"Lee","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3286826"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3352429"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-44"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890188.pdf?arnumber=10890188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:06Z","timestamp":1774416366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890188","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}