{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:46:55Z","timestamp":1784821615267,"version":"3.55.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001781","name":"Swinburne University of Technology Sarawak Higher Degree by Research (HDR) Support Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3163856","type":"journal-article","created":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T19:42:13Z","timestamp":1648755733000},"page":"36018-36027","source":"Crossref","is-referenced-by-count":167,"title":["Hybrid LSTM-Transformer Model for Emotion Recognition From Speech Audio Files"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0358-7655","authenticated-orcid":false,"given":"Felicia","family":"Andayani","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Computing, and Science, Swinburne University of Technology Sarawak Campus, Kuching, Sarawak, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lau Bee","family":"Theng","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Computing, and Science, Swinburne University of Technology Sarawak Campus, Kuching, Sarawak, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4413-2000","authenticated-orcid":false,"given":"Mark Teekit","family":"Tsun","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Computing, and Science, Swinburne University of Technology Sarawak Campus, Kuching, Sarawak, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caslon","family":"Chua","sequence":"additional","affiliation":[{"name":"Faculty of Science, Engineering and Technology, Swinburne University of Technology, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Speech emotion recognition using convolution neural networks","author":"shahsavarani","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2021.0120422"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.01.098"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108046"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIMA50015.2021.9526323"},{"key":"ref34","article-title":"Speech emotion recognition from raw audio using deep learning","author":"rintala","year":"2020"},{"key":"ref10","author":"tanikawa","year":"2020","journal-title":"Text Generation With LSTM+Transformer Model (Japanese)"},{"key":"ref11","first-page":"50","article-title":"Combining RNN with transformer for modeling multi-leg trips","author":"sakatani","year":"2021","journal-title":"Proc ACM WSDM WebTour"},{"key":"ref12","author":"mcfee","year":"2020","journal-title":"Librosa\/librosa"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2753"},{"key":"ref17","first-page":"1701","article-title":"Learning temporal clusters using capsule routing for speech emotion recognition","author":"md jalal","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5539-3"},{"key":"ref19","article-title":"TRANS-BLSTM: Transformer with bidirectional LSTM for language understanding","author":"huang","year":"2020","journal-title":"arXiv 2003 07000"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC46691.2019.8939830"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5120\/17201-7409"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"14","DOI":"10.3389\/fcomp.2020.00014","article-title":"Real-time speech emotion recognition using a pre-trained image classification network: Effects of bandwidth reduction and companding","volume":"2","author":"lech","year":"2020","journal-title":"Frontiers Comput Sci"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2925934"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053581"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462677"},{"key":"ref8","article-title":"Bimodal speech emotion recognition using pre-trained language models","author":"heusser","year":"2019","journal-title":"arXiv 1912 02610"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv 1706 03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ATSIP.2017.8075575"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s20226688"},{"key":"ref1","article-title":"Speech emotion recognition","author":"sidorova","year":"2007"},{"key":"ref20","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref22","first-page":"1","article-title":"Automatic speech emotion recognition using machine learning","author":"kerkeni","year":"2019","journal-title":"Proc Social Media Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5220\/0006611601750182"},{"key":"ref24","author":"craft","year":"2018","journal-title":"Dialectical Behavior Therapy Control Your Emotions Overcome Mood Swings and Balance Your Life With DBT"},{"key":"ref23","first-page":"164","article-title":"Transformer-like model with linear attention for speech emotion recognition","volume":"37","author":"jing","year":"2021","journal-title":"J Southeast Univ"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417964"},{"key":"ref25","first-page":"52","article-title":"Speech emotion recognition based on three-chanel feature fusion of CNN and BiLSTM","author":"huang","year":"2020","journal-title":"Proc ICIAI"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09745599.pdf?arnumber=9745599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T00:37:02Z","timestamp":1659659822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9745599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3163856","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}