{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:58:18Z","timestamp":1776275898638,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887873","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Microphone Speech Emotion Recognition Using the Hierarchical Token-Semantic Audio Transformer Architecture"],"prefix":"10.1109","author":[{"given":"Ohad","family":"Cohen","sequence":"first","affiliation":[{"name":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gershon","family":"Hazan","sequence":"additional","affiliation":[{"name":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharon","family":"Gannot","sequence":"additional","affiliation":[{"name":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980032"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.smhl.2020.100165"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3144457.3144503"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICSEE.2018.8645989"},{"key":"ref6","article-title":"Challenges in acoustic signal enhancement for human-robot communication","volume-title":"Speech Communication; ITG Symposium","author":"L\u00f6llmann"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-018-0133-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2228"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2017.8019296"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289866"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/math8122133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/2645381"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.104886"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIC49074.2020.9051332"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15439\/2020F20"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2577502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715386"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887873.pdf?arnumber=10887873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:20Z","timestamp":1774416200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887873","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}