{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:05:33Z","timestamp":1775199933483,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434696","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["ULTRAS - Unified Learning of Transformer Representations for Audio and Speech Signals"],"prefix":"10.1109","author":[{"given":"P E","family":"Ameenudeen","sequence":"first","affiliation":[{"name":"Indian Institute of Science,LEAP Laboratory Electrical Engineering,Bangalore,India"}]},{"given":"Charumathi","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,LEAP Laboratory Electrical Engineering,Bangalore,India"}]},{"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,LEAP Laboratory Electrical Engineering,Bangalore,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref4","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":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275873"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02580"},{"key":"ref10","article-title":"From vision to audio and beyond: A unified model for audio-visual representation and generation","author":"Su","year":"2024","journal-title":"arXiv preprint arXiv:2409.19132"},{"key":"ref11","article-title":"BEATS: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv:2212.09058"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-506"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3352248"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389636"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref21","article-title":"Speech Commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv preprint arXiv:1804.03209"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref23","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International conference on machine learning.","author":"Engel"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434696.pdf?arnumber=11434696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:23Z","timestamp":1775192303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434696","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}