{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:58:27Z","timestamp":1780534707901,"version":"3.54.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746820","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"9226-9230","source":"Crossref","is-referenced-by-count":22,"title":["Audio Deepfake Detection System with Neural Stitching for ADD 2022"],"prefix":"10.1109","author":[{"given":"Rui","family":"Yan","sequence":"first","affiliation":[{"name":"Beike,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Wen","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuran","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingwei","family":"Guo","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zou","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangang","family":"Li","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-948"},{"key":"ref11","first-page":"2","article-title":"Mish: A self regularized non-monotonic neural activation function","volume":"4","author":"misra","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298701"},{"key":"ref14","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.1872572"},{"key":"ref18","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462025"},{"key":"ref4","article-title":"How deep are the fakes? focusing on audio deepfake: A survey","author":"khanjani","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2616"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref8","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref7","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414788"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053217"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746820.pdf?arnumber=9746820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:09:06Z","timestamp":1660579746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746820","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}