{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:17Z","timestamp":1774419617680,"version":"3.50.1"},"reference-count":27,"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\/icassp49660.2025.10889924","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":0,"title":["Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models"],"prefix":"10.1109","author":[{"given":"Li-Wei","family":"Chen","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Takuya","family":"Higuchi","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"He","family":"Bai","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Ahmed Hussen","family":"Abdelaziz","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Alexander","family":"Rudnicky","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Tatiana","family":"Likhomanenko","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Barry-John","family":"Theobald","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Zakaria","family":"Aldeneh","sequence":"additional","affiliation":[{"name":"Apple"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref8","first-page":"18003","article-title":"ContentVec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref9","article-title":"Multi-resolution huBERT: Multi-resolution speech self-supervised learning with masked unit prediction","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shi"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref14","first-page":"1399","article-title":"A3T: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"International Conference on Machine Learning","author":"Bai"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref18","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"key":"ref23","article-title":"Speechtokenizer: Unified speech tokenizer for speech language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2251"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","article-title":"The faiss library","author":"Douze","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"}],"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\/10889924.pdf?arnumber=10889924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:46Z","timestamp":1774416226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889924","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}