{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:50:03Z","timestamp":1750308603374,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,12,21]],"date-time":"2018-12-21T00:00:00Z","timestamp":1545350400000},"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":[[2018,12,21]]},"DOI":"10.1145\/3302425.3302444","type":"proceedings-article","created":{"date-parts":[[2019,2,6]],"date-time":"2019-02-06T19:17:35Z","timestamp":1549480655000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Speech Emotion Recognition Based on LSTM and Mel Scale Wavelet Packet Decomposition"],"prefix":"10.1145","author":[{"given":"Tian","family":"Feng","sequence":"first","affiliation":[{"name":"Key Laboratory of Computer Vision & System, Ministry of Education, Tianjin University of Technology, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuying","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,12,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Emotion recognition in speech using neural networks{C}\/\/ International Conference on Neural Information Processing","author":"Nicholson J","year":"1999","unstructured":"Nicholson J , Takahashi K , Nakatsu R. Emotion recognition in speech using neural networks{C}\/\/ International Conference on Neural Information Processing , 1999 . Proceedings. ICONIP. IEEE , 2000: 495--501 vol. 2 . Nicholson J, Takahashi K, Nakatsu R. Emotion recognition in speech using neural networks{C}\/\/ International Conference on Neural Information Processing, 1999. Proceedings. ICONIP. IEEE, 2000:495--501 vol.2."},{"key":"e_1_3_2_1_2_1","volume-title":"Hidden Markov model-based speech emotion recognition{C}\/\/ International Conference on Multimedia and Expo","author":"Schuller B","year":"2003","unstructured":"Schuller B , Rigoll G , Lang M. Hidden Markov model-based speech emotion recognition{C}\/\/ International Conference on Multimedia and Expo , 2003 . ICME '03. Proceedings. IEEE , 2003:I-401-4 vol. 1 . Schuller B, Rigoll G, Lang M. Hidden Markov model-based speech emotion recognition{C}\/\/ International Conference on Multimedia and Expo, 2003. ICME '03. Proceedings. IEEE, 2003:I-401-4 vol.1."},{"issue":"4","key":"e_1_3_2_1_3_1","first-page":"389","article-title":"Emotion recognition in human-computer interaction{J}","volume":"18","author":"Cowie R","year":"2005","unstructured":"Cowie R , Douglascowie E , Tsapatsoulis N , Emotion recognition in human-computer interaction{J} . IEEE Signal Processing Magazine , 2005 , 18 ( 4 ): 389 . Cowie R, Douglascowie E, Tsapatsoulis N, et al. Emotion recognition in human-computer interaction{J}. IEEE Signal Processing Magazine, 2005, 18(4):389.","journal-title":"IEEE Signal Processing Magazine"},{"key":"e_1_3_2_1_4_1","volume-title":"Ninth International Conference on Spoken Language Processing","author":"Kao Y H","year":"2006","unstructured":"Kao Y H , Lee L S . Feature analysis for emotion recognition from Mandarin speech considering the special characteristics of Chinese language{C}\/\/ INTERSPEECH 2006 - Icslp , Ninth International Conference on Spoken Language Processing , Pittsburgh, Pa, Usa, September. DBLP , 2006 . Kao Y H, Lee L S. Feature analysis for emotion recognition from Mandarin speech considering the special characteristics of Chinese language{C}\/\/ INTERSPEECH 2006 - Icslp, Ninth International Conference on Spoken Language Processing, Pittsburgh, Pa, Usa, September. DBLP, 2006."},{"volume-title":"Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. IEEE","author":"Lugger M","key":"e_1_3_2_1_5_1","unstructured":"Lugger M , Yang B , Wokurek W. Robust Estimation of Voice Quality Parameters Under Realworld Disturbances{C}\/\/ IEEE International Conference on Acoustics , Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. IEEE , 2006:I-I. Lugger M, Yang B, Wokurek W. Robust Estimation of Voice Quality Parameters Under Realworld Disturbances{C}\/\/ IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. IEEE, 2006:I-I."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5120\/11872-7667"},{"key":"e_1_3_2_1_7_1","first-page":"3780","article-title":"Emotional feature selection of speaker-independent speech based on correlation analysis and Fisher{C}\/\/ Control Conference","volume":"2015","author":"Liu Z T","unstructured":"Liu Z T , Li K , Li D Y , Emotional feature selection of speaker-independent speech based on correlation analysis and Fisher{C}\/\/ Control Conference . IEEE , 2015 : 3780 -- 3784 . Liu Z T, Li K, Li D Y, et al. Emotional feature selection of speaker-independent speech based on correlation analysis and Fisher{C}\/\/ Control Conference. IEEE, 2015:3780--3784.","journal-title":"IEEE"},{"key":"e_1_3_2_1_8_1","volume-title":"Research on Speech Emotion Recognition {D}. South China university of technology","author":"Lin Y L","year":"2006","unstructured":"Lin Y L . Research on Speech Emotion Recognition {D}. South China university of technology , 2006 . Lin Y L. Research on Speech Emotion Recognition {D}. South China university of technology, 2006."},{"key":"e_1_3_2_1_9_1","volume-title":"Hierarchical Convolutional Deep Learning in Computer Vision","author":"Zeiler","year":"2013","unstructured":"M.D. Zeiler , Hierarchical Convolutional Deep Learning in Computer Vision , New York University , 2013 . M.D. Zeiler, Hierarchical Convolutional Deep Learning in Computer Vision, New York University, 2013."},{"key":"e_1_3_2_1_10_1","first-page":"2551","volume-title":"2010 IEEE Conference on","author":"Ranzato G.E.","year":"2010","unstructured":"M. Ranzato , G.E. Hinton, Modeling pixel means and covariances using factor- ized third-order Boltzmann machines, in: Computer Vision and Pattern Recog- nition (CVPR) , 2010 IEEE Conference on , 2010 , pp. 2551 -- 2558 . M. Ranzato, G.E. Hinton, Modeling pixel means and covariances using factor- ized third-order Boltzmann machines, in: Computer Vision and Pattern Recog- nition (CVPR), 2010 IEEE Conference on, 2010, pp. 2551--2558."},{"key":"e_1_3_2_1_11_1","first-page":"20","article-title":"Lee, Sparse deep belief net models for visual area V2","author":"Ekanadham S.","year":"2008","unstructured":"C. Ekanadham , S. Reader , H . Lee, Sparse deep belief net models for visual area V2 , Adv. Neural Inf. Process. Syst. 20 ( 2008 ). C. Ekanadham, S. Reader, H. Lee, Sparse deep belief net models for visual area V2, Adv. Neural Inf. Process. Syst. 20 (2008).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1626431.1626476"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495072"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"e_1_3_2_1_17_1","volume-title":"A Signal Processing Approach","author":"Sundararajan D.","year":"2015","unstructured":"Sundararajan D. 12. The Discrete Wavelet Packet Transform{M}\/\/ Discretewavelet Transform : A Signal Processing Approach . John Wiley & Sons, Singapore Pte . Ltd , 2015 : 163--191. Sundararajan D.12.The Discrete Wavelet Packet Transform{M}\/\/ Discretewavelet Transform: A Signal Processing Approach. John Wiley & Sons, Singapore Pte. Ltd, 2015:163--191."},{"key":"e_1_3_2_1_18_1","volume-title":"Auditory model based modified MFCC features{J}","author":"Main","year":"2010","unstructured":"Main . Auditory model based modified MFCC features{J} . 2010 . Main. Auditory model based modified MFCC features{J}. 2010."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"event":{"name":"ACAI 2018: 2018 International Conference on Algorithms, Computing and Artificial Intelligence","sponsor":["The Hong Kong Polytechnic The Hong Kong Polytechnic University","City University of Hong Kong City University of Hong Kong"],"location":"Sanya China","acronym":"ACAI 2018"},"container-title":["Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302425.3302444","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3302425.3302444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:05:45Z","timestamp":1750273545000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302425.3302444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,21]]},"references-count":19,"alternative-id":["10.1145\/3302425.3302444","10.1145\/3302425"],"URL":"https:\/\/doi.org\/10.1145\/3302425.3302444","relation":{},"subject":[],"published":{"date-parts":[[2018,12,21]]},"assertion":[{"value":"2018-12-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}