{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T21:46:13Z","timestamp":1774647973340,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023098","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"519-523","source":"Crossref","is-referenced-by-count":33,"title":["Speech Emotion Recognition Using Speech Feature and Word Embedding"],"prefix":"10.1109","author":[{"given":"Bagus Tris","family":"Atmaja","sequence":"first","affiliation":[]},{"given":"Kiyoaki","family":"Shirai","sequence":"additional","affiliation":[]},{"given":"Masato","family":"Akagi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"15","article-title":"Recognizing emotions in dialogues with disfluencies and non-verbal vocalisations","volume":"14","author":"leimin","year":"0","journal-title":"Proceedings of the 4th Interdisciplinary Workshop on Laughter and Other Non-verbal Vocalisations in Speech"},{"key":"ref11","author":"dzmitry","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref12","author":"seunghyun","year":"2018","journal-title":"Multimodal Speech Emotion Recognition Using Audio and Text"},{"key":"ref13","first-page":"1532","article-title":"Glove: Global vectors for word representation","author":"jeffrey","year":"0","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref14","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":"carlos","year":"2008","journal-title":"Language Resources and Evaluation"},{"key":"ref15","first-page":"939","article-title":"A Comparison of Sequence-to-Sequence Models for Speech Recognition","author":"rohit","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","first-page":"5300","article-title":"Recurrent convolutional neural network for speech processing","author":"yue","year":"0","journal-title":"2017 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref17","author":"vladimir","year":"2017","journal-title":"Emotion Recognition From Speech With Recurrent Neural Networks"},{"key":"ref18","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"yarin","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","author":"michael","year":"2017","journal-title":"Attentive Convolutional Neural Network based Speech Emotion Recognition A Study on the Impact of Input Features Signal Length and Acted Speech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2466"},{"key":"ref3","author":"alon","year":"2009","journal-title":"The unreasonable effectiveness of data"},{"key":"ref6","first-page":"6","article-title":"Combining Acoustic and Language Information for Emotion Recognition","volume":"2002","author":"lee","year":"2002","journal-title":"ICSLP 2002"},{"key":"ref5","first-page":"3688","author":"yenigalla","year":"2018","journal-title":"Speech Emotion Recognition Using Spectrogram & Phoneme Embedding"},{"key":"ref8","first-page":"1","article-title":"Combining speech-based and linguistic classifiers to recognize emotion in user spoken utterances","author":"griol","year":"2017","journal-title":"Neurocomputing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref2","author":"samarth","year":"2018","journal-title":"Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning"},{"key":"ref1","first-page":"22","article-title":"Emotion in speech: Recognition and application to call centers","volume":"710","author":"valery","year":"0","journal-title":"Proceedings of Artificial Neural Networks in Engineering"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Lanzhou, China","start":{"date-parts":[[2019,11,18]]},"end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023098.pdf?arnumber=9023098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:55:34Z","timestamp":1658094934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023098","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}