{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T01:09:16Z","timestamp":1760404156586,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8794468","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"7976-7982","source":"Crossref","is-referenced-by-count":18,"title":["Incorporating End-to-End Speech Recognition Models for Sentiment Analysis"],"prefix":"10.1109","author":[{"given":"Egor","family":"Lakomkin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Ali","family":"Zamani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sven","family":"Magg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MFI.2012.6343022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref34","first-page":"619","author":"d\u00e1vila-chac\u00f3n","year":"2014","journal-title":"Improving Humanoid Robot Speech Recognition with Sound Source Localisation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref11","first-page":"2379","article-title":"Hybrid Attention based Multimodal Network for Spoken Language Classification","author":"gu","year":"2018","journal-title":"ACL"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136760"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-917"},{"journal-title":"Speech Emotion Recognition with Data Augmentation and Layerwise Learning Rate Adjustment","year":"2018","author":"etienne","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-51"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1637"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-868"},{"key":"ref18","first-page":"423","article-title":"Reusing Neural Speech Representations for Auditory Emotion Recognition","volume":"1","author":"lakomkin","year":"2017","journal-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3301"},{"key":"ref28","article-title":"Improved Regularization Techniques for End-to-End Speech Recognition","volume":"abs 1712 7108","author":"zhou","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref27","article-title":"Deep Speech: Scaling up end-to-end speech recognition","volume":"abs 1412 5567","author":"hannun","year":"2014","journal-title":"CoRR"},{"journal-title":"Affective Computing","year":"1997","author":"picard","key":"ref3"},{"journal-title":"Multi-attention Recurrent Network for Human Communication Comprehension","year":"2018","author":"zadeh","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref5","first-page":"1","article-title":"Ensemble of SVM Trees for Multimodal Emotion Recognition","author":"rozgi?","year":"2012","journal-title":"Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"4445","DOI":"10.1109\/ICRA.2018.8461058","article-title":"EmoRL: Real-time Acoustic Emotion Classification using Deep Reinforcement Learning","author":"lakomkin","year":"2018","journal-title":"Robotics and Automation (ICRA) 2018 IEEE International Conference on"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"journal-title":"Multiplicative LSTM for sequence modelling","year":"2016","author":"krause","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"journal-title":"Learning to Generate Reviews and Discovering Sentiment","year":"2017","author":"radford","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00292"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","first-page":"173","article-title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2019,5,20]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08794468.pdf?arnumber=8794468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:09:06Z","timestamp":1657854546000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794468","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}