{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T13:29:03Z","timestamp":1772890143599,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Foundation for Aalto University Science and Technology"},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["337073"],"award-info":[{"award-number":["337073"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"name":"FIN-CLARIN as a Collaborative Platform for Speech Processing"},{"name":"Business Finland project LAREINA","award":["7817\/31\/2022"],"award-info":[{"award-number":["7817\/31\/2022"]}]},{"name":"Aalto ScienceIT"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3426301","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T17:42:29Z","timestamp":1720806149000},"page":"3546-3560","source":"Crossref","is-referenced-by-count":3,"title":["From Raw Speech to Fixed Representations: A Comprehensive Evaluation of Speech Embedding Techniques"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7219-9042","authenticated-orcid":false,"given":"Dejan","family":"Porjazovski","sequence":"first","affiliation":[{"name":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7918-9579","authenticated-orcid":false,"given":"Tam\u00e1s","family":"Gr\u00f3sz","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5278-7974","authenticated-orcid":false,"given":"Mikko","family":"Kurimo","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1963"},{"key":"ref3","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref4","first-page":"135","article-title":"Enriching word vectors with subword information","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"5","author":"Bojanowski","year":"2017"},{"key":"ref5","first-page":"4731","article-title":"High quality ELMo embeddings for seven less-resourced languages","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ular","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1204"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2194"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-82"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-678"},{"key":"ref11","article-title":"Language agnostic speech embeddings for emotion classification","volume-title":"Proc. ICML Workshop Self-Supervision Audio Speech","author":"Nandan","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861862"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-304"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414458"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846310"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","article-title":"Multi-view recurrent neural acoustic word embeddings","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2017"},{"key":"ref25","article-title":"Word-level acoustic modeling with convolutional vector regression","volume-title":"Proc. ICML Workshop Representation Learn.","author":"Maas","year":"2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"ref27","first-page":"178","article-title":"Pitch variations and emotions in speech","volume-title":"Proc. XIIIth Int. Congr. Phonetic Sci.","volume":"1","author":"Mozziconacci","year":"1995"},{"key":"ref28","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref29","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2394"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"ref34","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2362"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1823"},{"key":"ref40","first-page":"353","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"Proc. EMNLP Workshop Blackbox NLP: Analyzing Interpreting Neural Netw. NLP,","author":"Wang","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref46","first-page":"7252","article-title":"SLURP: A spoken language understanding resource package","volume-title":"Proc.Conf. Empirical Methods Natural Lang. Process.","author":"Bastianelli","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-022-09606-3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1159\/000091405"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-329"},{"key":"ref50","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3208121"},{"key":"ref52","article-title":"Prediction of user request and complaint in spoken customer-agent conversations","author":"Lackovic","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612835"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2000.861302"},{"issue":"12","key":"ref55","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","article-title":"Learning general purpose distributed sentence representations via large scale multi-task learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Subramanian","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289822"},{"key":"ref58","first-page":"6170","article-title":"XLM-E: Cross-lingual language model pre-training via ELECTRA","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Chi","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551572"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110814"},{"key":"ref61","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan","year":"2017"},{"key":"ref62","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref64","article-title":"A fine-tuned wav2vec 2.0\/Hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3606039.3613102"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10596685.pdf?arnumber=10596685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T05:02:54Z","timestamp":1722315774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10596685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3426301","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}