{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T10:51:13Z","timestamp":1756896673317,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891882","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["A Comparison Between Convolutional and Transformer Architectures for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Shreyah","family":"Iyer","sequence":"first","affiliation":[{"name":"School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK"}]},{"given":"Cornelius","family":"Glackin","sequence":"additional","affiliation":[{"name":"Intelligent Voice Ltd,London,UK"}]},{"given":"Nigel","family":"Cannings","sequence":"additional","affiliation":[{"name":"Intelligent Voice Ltd,London,UK"}]},{"given":"Vito","family":"Veneziano","sequence":"additional","affiliation":[{"name":"School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK"}]},{"given":"Yi","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK"}]}],"member":"263","reference":[{"journal-title":"Emotion recognition from speech using wav2vec 2 0 embeddings","year":"2021","author":"pepino","key":"ref39"},{"journal-title":"An ensemble ld-cnn-lstm-gru model with data augmentation for speech emotion recognition","year":"2021","author":"ahmed","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/e21050479"},{"key":"ref32","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2006","journal-title":"ArXiv"},{"key":"ref31","first-page":"18","article-title":"librosa: Audio and music signal analysis in python","volume":"8","author":"mcfee","year":"0","journal-title":"Proceedings of the 14th Python in Science Conference"},{"journal-title":"Dialogxl All-in-one xlnet for multi-party conversation emotion recognition","year":"2020","author":"shen","key":"ref30"},{"key":"ref37","first-page":"6309","article-title":"Speech emotion recognition using quater-nion convolutional neural networks","author":"muppidi","year":"0","journal-title":"ICASSP 2021 – 2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICECTA48151.2019.8959681"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref34","first-page":"13979","article-title":"Un-supervised cross-lingual representation learning for speech recognition","volume":"abs 2006","author":"conneau","year":"2020","journal-title":"CoRR"},{"key":"ref10","first-page":"206","article-title":"Nat-uralistic audio-visual emotion database","author":"kadiri","year":"2014","journal-title":"proceedings of the 11th International Conference on Natural Language Processing"},{"journal-title":"DialogueRNN An attentive RNN for emotion detection in conversations","year":"2019","author":"majumder","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIECS.2009.5362730"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2003.1280531"},{"key":"ref13","first-page":"205","article-title":"Analysis of emotional speech-a review","volume":"1","author":"paidi","year":"2016","journal-title":"Soc Believ Behav Syst"},{"key":"ref14","first-page":"1","article-title":"Speech emotion identification analysis based on different spectral feature ex-traction methods","author":"kamaruddin","year":"0","journal-title":"The 5th International Conference on Information and Communication Technology for The Muslim World (ICT4M)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"journal-title":"Speech Emotion Recognition Using Deep Neural Network and Extreme Learning Machine","year":"2014","author":"han","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2021.674853"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474198.3478152"},{"journal-title":"Improved speech emotion recognition using transfer learning and spectrogram augmentation","year":"2021","author":"padi","key":"ref19"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"Iemocap: interactive emotional dyadic motion capture database","volume":"42","author":"busso","year":"2008","journal-title":"Language Resources and Evaluation"},{"journal-title":"Statistical Methods for Speech Recognition","year":"1997","author":"jelinek","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"journal-title":"wav2vec 2 0 A framework for self-supervised learning of speech representations","year":"2020","author":"baevski","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCUBEA.2017.8463785"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCES45898.2019.9002175"},{"key":"ref8","first-page":"1989","volume":"3","author":"cowie","year":"1996","journal-title":"Automatic statistical analysis of the signal and prosodic signs of emotion in speech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/BigComp48618.2020.00014"},{"key":"ref2","volume":"9497","author":"al-talabani","year":"2015","journal-title":"Emotion recognition from speech Tools and challenges"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00071-7"},{"journal-title":"Stress detection through speech analysis","year":"2018","author":"tomba","key":"ref1"},{"key":"ref20","first-page":"1","volume":"4","author":"kadyrov","year":"2021","journal-title":"Speaker recognition from spectrogram images"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10101163"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18280\/ts.370107"},{"journal-title":"Multi-Window Data Augmentation Approach for Speech Emotion Recognition","year":"2021","author":"padi","key":"ref42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"journal-title":"EmoBERTa Speaker-Aware Emotion Recognition in Conversation with RoBERTa","year":"2021","author":"kim","key":"ref41"},{"key":"ref23","article-title":"Attention is all you need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref44","volume":"2","author":"ristea","year":"2020","journal-title":"Emotion recognition system from speech and visual information based on convolutional neural networks"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/s21227665"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891882.pdf?arnumber=9891882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:00:44Z","timestamp":1667516444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891882","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}