{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:54:08Z","timestamp":1764784448589,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,5,8]],"date-time":"2020-05-08T00:00:00Z","timestamp":1588896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,5,8]]},"DOI":"10.1145\/3390557.3394317","type":"proceedings-article","created":{"date-parts":[[2020,6,4]],"date-time":"2020-06-04T10:22:10Z","timestamp":1591266130000},"page":"52-58","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Speech Emotion Recognition Based on Three-Channel Feature Fusion of CNN and BiLSTM"],"prefix":"10.1145","author":[{"given":"Lilong","family":"Huang","sequence":"first","affiliation":[{"name":"Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering, Dalian University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Dong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering, Dalian University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering, Dalian University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,6,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the Interspeech. 502--505","author":"Boril H.","year":"2010","unstructured":"Boril , H. , Sadjadi , S.O. , Kleinschmidt , T. , Hansen , J.H.L. 2010 . Analysis and Detection of Cognitive Load and Frustration in Drivers' Speech . In Proceedings of the Interspeech. 502--505 . Boril, H., Sadjadi, S.O., Kleinschmidt, T., Hansen, J.H.L. 2010. Analysis and Detection of Cognitive Load and Frustration in Drivers' Speech. In Proceedings of the Interspeech. 502--505."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/10.846676"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 2012 Workshop on Child, Computer and Interaction. WOCCI. ISCA, Portland.","author":"Marchi E.","year":"2012","unstructured":"Marchi E. , Schuller B. , Batliner A. , Fridenzon S. , Tal S. , Golan O. 2012 . Emotion in the Speech of Children with Autism Spectrum Conditions: Prosody and Everything else . In Proceedings of the 2012 Workshop on Child, Computer and Interaction. WOCCI. ISCA, Portland. Marchi E., Schuller B., Batliner A., Fridenzon S., Tal S., Golan O. 2012. Emotion in the Speech of Children with Autism Spectrum Conditions: Prosody and Everything else. In Proceedings of the 2012 Workshop on Child, Computer and Interaction. WOCCI. ISCA, Portland."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72588-6_91"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the7th International Conference on Natural Computation. ICNC","author":"Wang W.S.","year":"2011","unstructured":"Wang , W.S. , Wu , J.B. 2011 . Emotion Recognition Based on CSO&SVM in E-learning . In Proceedings of the7th International Conference on Natural Computation. ICNC , Beijing, 566--570. Wang, W.S., Wu, J.B. 2011. Emotion Recognition Based on CSO&SVM in E-learning. In Proceedings of the7th International Conference on Natural Computation. ICNC, Beijing, 566--570."},{"volume-title":"Speech Emotion Recognition Using RBF Kernel of LIBSVM","author":"Chavhan Y. D.","key":"e_1_3_2_1_7_1","unstructured":"Chavhan , Y. D. , Yelure , B. S. , Tayade , K. 2015. Speech Emotion Recognition Using RBF Kernel of LIBSVM . In IEEE Sponsored 2ND International Conference on Electronics and Communication System. ICECS. IEEE, USA , 1132--1135. Chavhan, Y. D., Yelure, B. S., Tayade, K. 2015. Speech Emotion Recognition Using RBF Kernel of LIBSVM. In IEEE Sponsored 2ND International Conference on Electronics and Communication System. ICECS. IEEE, USA, 1132--1135."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CESYS.2017.8321292"},{"key":"e_1_3_2_1_9_1","volume-title":"An Experimental Study of Speech Emotion Recognition Based on Deep Convolutional Neural Networks. In International Conference on Affective Computing and Intelligent Interaction. ACII. IEEE, 827--831","author":"Zheng W. Q.","year":"2015","unstructured":"Zheng , W. Q. , Yu , J. S. , Zou , Y. X. 2015 . An Experimental Study of Speech Emotion Recognition Based on Deep Convolutional Neural Networks. In International Conference on Affective Computing and Intelligent Interaction. ACII. IEEE, 827--831 . Zheng, W. Q., Yu, J. S., Zou, Y. X. 2015. An Experimental Study of Speech Emotion Recognition Based on Deep Convolutional Neural Networks. In International Conference on Affective Computing and Intelligent Interaction. ACII. IEEE, 827--831."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Origlia A. Galata V. Ludusan B. 2010. Automatic classification of emotions via global and local prosodic features on a multilingual emotional database. In Processing of the 2010 Speech Prosody. Origlia A. Galata V. Ludusan B. 2010. Automatic classification of emotions via global and local prosodic features on a multilingual emotional database. In Processing of the 2010 Speech Prosody.","DOI":"10.21437\/SpeechProsody.2010-122"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-012-0352-1"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNIDC.2018.8525706"},{"key":"e_1_3_2_1_13_1","volume-title":"the 5th International Conference on Instrumentation and Measurement, Computer and Communication and Control. IEEE, 1109--1114","author":"Chen X.","year":"2015","unstructured":"Chen , X. , Li , H.F., Ma. L. , Liu , X.W. , Chen , Jing. 2015 . Teager_Mel and PLP Fusion Feature Based Speech Emotion Recognition . In the 5th International Conference on Instrumentation and Measurement, Computer and Communication and Control. IEEE, 1109--1114 . Chen, X., Li, H.F., Ma. L., Liu, X.W., Chen, Jing. 2015.Teager_Mel and PLP Fusion Feature Based Speech Emotion Recognition. In the 5th International Conference on Instrumentation and Measurement, Computer and Communication and Control. IEEE, 1109--1114."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCONS.2017.8250527"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1785455.1785458"},{"key":"e_1_3_2_1_16_1","volume-title":"Speech Based Human Emotion Recognition Using MFCC. In the IEEE WiSPNET 2017 conference. IEEE, 2257--2260","author":"Likitha M.S.","year":"2017","unstructured":"Likitha , M.S. , Gupta , S.R.R. , Hasitha , K. , Upendra Raju . A. 2017 . Speech Based Human Emotion Recognition Using MFCC. In the IEEE WiSPNET 2017 conference. IEEE, 2257--2260 . Likitha, M.S., Gupta, S.R.R., Hasitha, K., Upendra Raju. A. 2017. Speech Based Human Emotion Recognition Using MFCC. In the IEEE WiSPNET 2017 conference. IEEE, 2257--2260."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDT.2009.30"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ELECO.2015.7394435"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Bandela S. R. Kumar T. K. 2017. Stressed Speech Emotion Recognition using Feature Fusion of Teager Energy Operator and MFCC \/\/ 8th ICCCNT 2017 IIT Delhi Delhi India 3--5. Bandela S. R. Kumar T. K. 2017. Stressed Speech Emotion Recognition using Feature Fusion of Teager Energy Operator and MFCC \/\/ 8th ICCCNT 2017 IIT Delhi Delhi India 3--5.","DOI":"10.1109\/ICCCNT.2017.8204149"},{"key":"e_1_3_2_1_20_1","volume-title":"Speech Emotion Recognition Based on Deep Belief Network. In 2018 IEEE 15th International Conference on Networking, Sensing and Control. ICNSC. IEEE, 1--5.","author":"Peng Shi","year":"2018","unstructured":"Peng Shi . 2018 . Speech Emotion Recognition Based on Deep Belief Network. In 2018 IEEE 15th International Conference on Networking, Sensing and Control. ICNSC. IEEE, 1--5. Peng Shi. 2018. Speech Emotion Recognition Based on Deep Belief Network. In 2018 IEEE 15th International Conference on Networking, Sensing and Control. ICNSC. IEEE, 1--5."},{"key":"e_1_3_2_1_21_1","volume-title":"Speech Emotion Recognition with Deep Learning. In the 4th International Conference on Signal Processing and Integrated Networks. SPIN. IEEE, 137--140","author":"Har\u00e1r P.","year":"2017","unstructured":"Har\u00e1r , P. , Burget , R. , Dutta , M.K. 2017 . Speech Emotion Recognition with Deep Learning. In the 4th International Conference on Signal Processing and Integrated Networks. SPIN. IEEE, 137--140 . Har\u00e1r, P., Burget, R., Dutta, M.K. 2017. Speech Emotion Recognition with Deep Learning. In the 4th International Conference on Signal Processing and Integrated Networks. SPIN. IEEE, 137--140."},{"key":"e_1_3_2_1_22_1","volume-title":"3D CNN-Based Speech Emotion Recognition Using K-Means Clustering and Spectrograms. Entropy","author":"Hajarolasvadi N.","year":"2019","unstructured":"Hajarolasvadi , N. , Demirel , H. 2019. 3D CNN-Based Speech Emotion Recognition Using K-Means Clustering and Spectrograms. Entropy 2019 . 21, 479, 1--17. Hajarolasvadi, N., Demirel, H. 2019. 3D CNN-Based Speech Emotion Recognition Using K-Means Clustering and Spectrograms. Entropy 2019. 21, 479, 1--17."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"XIE Y. LIANG R.Y. LIANG Z L. ZHAO L. 2019. Attention-Based Dense LSTM for Speech Emotion Recognition. In 2019 The Institute of Electronics Information and Communication Engineers. IEICE TRANS. INF. Syst. E102--D 7 1426--1429. XIE Y. LIANG R.Y. LIANG Z L. ZHAO L. 2019. Attention-Based Dense LSTM for Speech Emotion Recognition. In 2019 The Institute of Electronics Information and Communication Engineers. IEICE TRANS. INF. Syst. E102--D 7 1426--1429.","DOI":"10.1587\/transinf.2019EDL8019"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"e_1_3_2_1_25_1","volume-title":"Attention-Based BiLSTM Network with Lexical Feature for Emotion Classification. In 2018 International Joint Conference on Neural Network. IJCNN. IEEE, 1--8.","author":"Gao K.","year":"2018","unstructured":"Gao , K. , Xu , H. , Gao , L. , Hao , H.Y. , Deng , J.H. , Sun , X.M. 2018 . Attention-Based BiLSTM Network with Lexical Feature for Emotion Classification. In 2018 International Joint Conference on Neural Network. IJCNN. IEEE, 1--8. Gao, K., Xu, H., Gao, L., Hao, H.Y., Deng, J.H., Sun, X.M. 2018. Attention-Based BiLSTM Network with Lexical Feature for Emotion Classification. In 2018 International Joint Conference on Neural Network. IJCNN. IEEE, 1--8."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"volume-title":"Long short-term memory. Neural computation","author":"Hochreiter J.","key":"e_1_3_2_1_27_1","unstructured":"S. Hochreiter and J. Schmidhuber . 1997. Long short-term memory. Neural computation , vol. 9 , no. 8. 1735--1780. S.Hochreiter and J.Schmidhuber. 1997. Long short-term memory. Neural computation, vol. 9, no. 8. 1735--1780."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Sak H. Senior A. Beaufays F. 2014. Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128. Sak H. Senior A. Beaufays F. 2014. Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128.","DOI":"10.21437\/Interspeech.2014-80"},{"key":"e_1_3_2_1_29_1","unstructured":"http:\/\/www.chineseldc.org\/resource_info.php?rid=76[EB\/OL]. http:\/\/www.chineseldc.org\/resource_info.php?rid=76[EB\/OL]."},{"volume-title":"Ninth European Conference on Speech Communication and Technology.","author":"Burkhardt F.","key":"e_1_3_2_1_30_1","unstructured":"Burkhardt , F. , Paeschke , A. , Rolfes , M. , and Weiss , B . 2005. A database of German emotional speech . In Ninth European Conference on Speech Communication and Technology. Burkhardt, F., Paeschke, A., Rolfes, M., and Weiss, B. 2005. A database of German emotional speech. In Ninth European Conference on Speech Communication and Technology."},{"key":"e_1_3_2_1_31_1","unstructured":"https:\/\/librosa.github.io\/librosa\/index.html. https:\/\/librosa.github.io\/librosa\/index.html."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2018.8407844"},{"key":"e_1_3_2_1_33_1","article-title":"Emotion Recognition Based on Deep Belief Network","author":"Zhang L.","year":"2019","unstructured":"Zhang , L. , Yan , Q. , Liu , J.H. 2019 . Emotion Recognition Based on Deep Belief Network . Journal of TaiYuan University of Technology, 101--107. Zhang, L., Yan, Q., Liu, J.H. 2019. Emotion Recognition Based on Deep Belief Network. Journal of TaiYuan University of Technology, 101--107.","journal-title":"Journal of TaiYuan University of Technology, 101--107."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"e_1_3_2_1_35_1","volume-title":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. APSIPA. IEEE, 1--4.","author":"Lim W.","year":"2017","unstructured":"Lim , W. , Jang , D. , Lee , T. 2017 . Speech Emotion Recognition using Convolutional and Recurrent Neural Networks . In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. APSIPA. IEEE, 1--4. Lim, W., Jang, D., Lee, T. 2017. Speech Emotion Recognition using Convolutional and Recurrent Neural Networks. In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. APSIPA. IEEE, 1--4."}],"event":{"name":"ICIAI 2020: 2020 the 4th International Conference on Innovation in Artificial Intelligence","sponsor":["The Hong Kong Polytechnic The Hong Kong Polytechnic University","Xi'an Jiaotong-Liverpool University Xi'an Jiaotong-Liverpool University"],"location":"Xiamen China","acronym":"ICIAI 2020"},"container-title":["Proceedings of the 2020 the 4th International Conference on Innovation in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3390557.3394317","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3390557.3394317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:36Z","timestamp":1750199916000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3390557.3394317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,8]]},"references-count":35,"alternative-id":["10.1145\/3390557.3394317","10.1145\/3390557"],"URL":"https:\/\/doi.org\/10.1145\/3390557.3394317","relation":{},"subject":[],"published":{"date-parts":[[2020,5,8]]},"assertion":[{"value":"2020-06-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}