{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T07:46:36Z","timestamp":1776152796796,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62076184"],"award-info":[{"award-number":["62076184"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673299"],"award-info":[{"award-number":["61673299"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976160"],"award-info":[{"award-number":["61976160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076182"],"award-info":[{"award-number":["62076182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Innovation Action Project of Science and Technology","award":["20511100700"],"award-info":[{"award-number":["20511100700"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["22ZR1466700"],"award-info":[{"award-number":["22ZR1466700"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3282488","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T19:53:17Z","timestamp":1685735597000},"page":"1395-1406","source":"Crossref","is-referenced-by-count":4,"title":["Explainability of Speech Recognition Transformers via Gradient-Based Attention Visualization"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9386-0864","authenticated-orcid":false,"given":"Tianli","family":"Sun","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"given":"Haonan","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9448-9892","authenticated-orcid":false,"given":"Guosheng","family":"Hu","sequence":"additional","affiliation":[{"name":"Oosto, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5250-170X","authenticated-orcid":false,"given":"Lianghua","family":"He","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-9674","authenticated-orcid":false,"given":"Cairong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.008"},{"key":"ref8","first-page":"3543","article-title":"Attention is not explanation","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Jain","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref13","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref14","first-page":"1","article-title":"Neuron activation profiles for interpreting convolutional speech recognition models","volume-title":"Proc. NeurIPS Workshop Interpretability Robustness Audio, Speech, Lang.","author":"Krug","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054675"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3101921"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref26","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190927"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10143311.pdf?arnumber=10143311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:51:33Z","timestamp":1705690293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10143311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3282488","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}