{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:41:23Z","timestamp":1778604083251,"version":"3.51.4"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icasspw59220.2023.10193151","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T13:30:54Z","timestamp":1690983054000},"page":"1-5","source":"Crossref","is-referenced-by-count":37,"title":["A Vector Quantized Masked Autoencoder for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Samir","family":"Sadok","sequence":"first","affiliation":[{"name":"CentraleSupélec, IETR UMR CNRS 6164,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Leglaive","sequence":"additional","affiliation":[{"name":"CentraleSupélec, IETR UMR CNRS 6164,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renaud","family":"S\u00e9guier","sequence":"additional","affiliation":[{"name":"CentraleSupélec, IETR UMR CNRS 6164,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","article-title":"Neural discrete representation learning","volume":"30","author":"den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Masked autoencoders that listen","author":"xu","year":"2022","journal-title":"arXiv preprint arXiv 2207 06405"},{"key":"ref11","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"1 (long and short papers)","author":"devlin","year":"2019","journal-title":"Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref17","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref19","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","article-title":"Vector-quantized image modeling with improved vqgan","author":"yu","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956592"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref20","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv preprint arXiv 1706 02677"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref21","article-title":"Query2label: A simple transformer way to multi-label classification","author":"liu","year":"2021","journal-title":"arXiv preprint arXiv 2107 10834"},{"key":"ref8","article-title":"A survey on masked autoencoder for self-supervised learning in vision and beyond","author":"zhang","year":"2022","journal-title":"arXiv preprint arXiv 2208 02403"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref4","article-title":"Exploring wav2vec 2.0 fine-tuning for improved speech emotion recognition","author":"chen","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref3","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"wang","year":"2021","journal-title":"arXiv preprint arXiv 2111 02269"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193151.pdf?arnumber=10193151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T13:42:27Z","timestamp":1692625347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193151","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}