{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T22:15:22Z","timestamp":1779228922875,"version":"3.51.4"},"reference-count":46,"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\/icassp49357.2023.10096248","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Neural Architecture of Speech"],"prefix":"10.1109","author":[{"given":"Subba Reddy","family":"Oota","sequence":"first","affiliation":[{"name":"Inria Bordeaux,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khushbu","family":"Pahwa","sequence":"additional","affiliation":[{"name":"University of California, LA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mounika","family":"Marreddy","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manish","family":"Gupta","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bapi S.","family":"Raju","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref35","first-page":"10937","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","author":"wang","year":"2021","journal-title":"ICML"},{"key":"ref13","article-title":"Toward a realistic model of speech processing in the brain with self-supervised learning","author":"millet","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5974"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","article-title":"Many but not all deep neural network audio models capture brain responses and exhibit hierarchical region correspondence","author":"tuckute","year":"2022","journal-title":"BioRxiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref14","article-title":"Self-supervised models of audio effectively explain human cortical responses to speech","author":"vaidya","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747332"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature17637"},{"key":"ref32","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1050"},{"key":"ref1","first-page":"8","article-title":"Deep learning for brain encoding and decoding","volume":"44","author":"oota","year":"2022","journal-title":"Proceedings of the Annual Meeting of the Cognitive Science Society"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10269"},{"key":"ref17","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref16","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref46","article-title":"Self-supervised models of audio effectively explain human cortical responses to speech","author":"vaidya","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref45","article-title":"Visio-linguistic brain encoding","author":"oota","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref42","article-title":"Modeling task effects on meaning representation in the brain via zero-shot meg prediction","volume":"33","author":"toneva","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.308"},{"key":"ref44","first-page":"105","article-title":"Multi-view and cross-view brain decoding","author":"oota","year":"2022","journal-title":"COLING"},{"key":"ref22","article-title":"Non-autoregressive predictive coding for learning speech representations from local dependencies","author":"liu","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.235"},{"key":"ref21","article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","author":"ling","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref27","first-page":"344","article-title":"Audio albert: A lite bert for selfsupervised learning of audio representation","author":"chi","year":"2021","journal-title":"SLT Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref8","article-title":"The neural architecture of language: Integrative reverse-engineering converges on a model for predictive processing","author":"schrimpf","year":"2020","journal-title":"BioRxiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref9","first-page":"407007","article-title":"Brain-score: Which artificial neural network for object recognition is most brain-like?","author":"schrimpf","year":"2020","journal-title":"BioRxiv"},{"key":"ref4","first-page":"14123","article-title":"Inducing brain-relevant bias in natural language processing models","volume":"32","author":"schwartz","year":"2019","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)","author":"toneva","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5647"},{"key":"ref5","article-title":"From voxels to pixels and back: Self-supervision in natural-image reconstruction from fmri","author":"beliy","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0112575"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096248.pdf?arnumber=10096248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:04:18Z","timestamp":1700507058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096248","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}