{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:16:36Z","timestamp":1776442596078,"version":"3.51.2"},"reference-count":31,"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\/icassp49660.2025.10890012","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":1,"title":["Effective Techniques for Scaling Audio Encoder Pretraining"],"prefix":"10.1109","author":[{"given":"Byeonggeun","family":"Kim","sequence":"first","affiliation":[{"name":"Amazon AGI,Bellevue,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Bydlon","sequence":"additional","affiliation":[{"name":"Amazon AGI,Boston,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingming","family":"Tang","sequence":"additional","affiliation":[{"name":"Amazon AGI,Boston,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huy","family":"Phan","sequence":"additional","affiliation":[{"name":"Amazon AGI,Cambridge,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chieh-Chi","family":"Kao","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bellevue,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Amazon AGI,Boston,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon AGI,Boston,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","volume":"abs\/2311.07919","author":"Chu","year":"2023","journal-title":"CoRR"},{"key":"ref2","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref5","article-title":"Masked autoencoders that listen","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022","author":"Huang"},{"key":"ref6","article-title":"Beats: Audio pre-training with acoustic tokenizers","volume-title":"International Conference on Machine Learning, ICML 2023","author":"Chen"},{"key":"ref7","article-title":"A-JEPA: joint-embedding predictive architecture can listen","volume":"abs\/2311.15830","author":"Fei","year":"2023","journal-title":"CoRR"},{"key":"ref8","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning, ICML 2023","author":"Radford"},{"key":"ref9","article-title":"Mavil: Masked audio-video learners","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023","author":"Huang"},{"key":"ref10","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Zhu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"in 9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref15","article-title":"The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use","author":"Sturm","year":"2013","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979822"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746828"},{"key":"ref19","article-title":"MERT: Acoustic music understanding model with large-scale self-supervised training","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3506286"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053174"},{"key":"ref25","article-title":"Mustango: Toward controllable text-to-music generation","author":"Melechovsky","year":"2023","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref27","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref28","article-title":"Decoupled weight decay regularization","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref30","article-title":"BERT: pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","author":"Devlin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.427"}],"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\/10890012.pdf?arnumber=10890012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:39Z","timestamp":1774416279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890012","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}