{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T04:17:51Z","timestamp":1750911471674},"reference-count":21,"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\/icassp43922.2022.9746403","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4813-4817","source":"Crossref","is-referenced-by-count":2,"title":["An Audio-Saliency Masking Transformer for Audio Emotion Classification in Movies"],"prefix":"10.1109","author":[{"given":"Ya-Tse","family":"Wu","sequence":"first","affiliation":[{"name":"National Tsing Hua University,Department of Electrical Engineering,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeng-Lin","family":"Li","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Department of Electrical Engineering,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Chun","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Department of Electrical Engineering,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-017-0194-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946961"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472192"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref15","first-page":"arxiv?2010","article-title":"Attendaffectnet: Self-attention based networks for predicting affective responses from movies","author":"thao","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2005.09.040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206076"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref19","first-page":"1206","article-title":"Using auditory saliency to understand complex auditory scenes","author":"duangudom","year":"2007","journal-title":"2007 15th European Signal Processing Conference"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267205"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-012-1046-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.copsyc.2018.10.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.30.051606.094256"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1721"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2305573"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/KCIC.2018.8628592"},{"article-title":"A saliency-based attention lstm model for cognitive load classification from speech","year":"2019","author":"antol\u00edn","key":"ref9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.5002886"},{"key":"ref21","first-page":"163","article-title":"A cross-linguistic comparison of perception to formant frequency cues in emotional speech","author":"erickson","year":"2008","journal-title":"COCOS"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09746403.pdf?arnumber=9746403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:14:30Z","timestamp":1661199270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746403","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}