{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:22:35Z","timestamp":1767705755519,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972168"],"award-info":[{"award-number":["61972168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3224295","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T19:39:47Z","timestamp":1669318787000},"page":"277-289","source":"Crossref","is-referenced-by-count":11,"title":["STFF-SM: Steganalysis Model Based on Spatial and Temporal Feature Fusion for Speech Streams"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1591-656X","authenticated-orcid":false,"given":"Hui","family":"Tian","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National Huaqiao University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6653-1734","authenticated-orcid":false,"given":"Yiqin","family":"Qiu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National Huaqiao University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8509-4127","authenticated-orcid":false,"given":"Wojciech","family":"Mazurczyk","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1622-0561","authenticated-orcid":false,"given":"Zhenxing","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","first-page":"1131","article-title":"Steganalysis of adaptive multi-rate speech using statistical characteristics of pitch delay","volume":"25","author":"tian","year":"2019","journal-title":"J Universal Comput Sci"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2636087"},{"key":"ref31","first-page":"2107","article-title":"Detection of pitch modulation information hiding based on codebook correlation network","volume":"37","author":"li","year":"2014","journal-title":"Chin J Comput"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00790-w"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref36","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"0","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref35","first-page":"1308","article-title":"Steganalysis of adaptive multi-rate speech streams based on the correlation of fractional pitch delay","volume":"45","author":"tian","year":"2022","journal-title":"Chin J Comput"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21373-2_21"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2012.6469943"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2024732"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PDGC.2014.7030779"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4055-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2218599"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6600-6"},{"key":"ref21","first-page":"1774","article-title":"Steganography for low bit-rate speech based on pitch period prediction","volume":"32","author":"yan","year":"2015","journal-title":"Appl Res Comput"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6867-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11389-6_21"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115834"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2020.1757520"},{"key":"ref50","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"Proc 7th Int Conf Learn Represent"},{"key":"ref51","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref52","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518532"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2012.05.003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref12","first-page":"1","article-title":"Notice of removal: Steganography in speech signal with enhanced multi-pulse excitation codevector with reduced number of bits","author":"tahilramani","year":"0","journal-title":"Proc IEEE Int Conf Elect Electron Signals Commun Optim"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2905760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02938-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2008.ECP.375"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-013-0302-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-015-0500-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7080673"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IIH-MSP.2009.83"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CICT.2016.34"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.03.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2011.2108649"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2002.802005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2372313"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxr111"},{"year":"2022","key":"ref49","article-title":"5G media streaming (5GMS); speech and audio profiles"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s21041032"},{"key":"ref46","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume":"70","author":"dauphin","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"year":"2022","key":"ref48","article-title":"Digital cellular telecommunications system (Phase 2+) (GSM); universal mobile telecommunications system (UMTS); speech codec list for GSM and UMTS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2806741"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.469"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09961950.pdf?arnumber=9961950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:28:35Z","timestamp":1672082915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9961950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3224295","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2023]]}}}