{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:11:41Z","timestamp":1775200301387,"version":"3.50.1"},"reference-count":28,"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\/asru65441.2025.11434788","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":["Benchmarking Rotary Position Embeddings for Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Shucong","family":"Zhang","sequence":"first","affiliation":[{"name":"AI Center, Samsung,Cambridge,UK"}]},{"given":"Titouan","family":"Parcollet","sequence":"additional","affiliation":[{"name":"AI Center, Samsung,Cambridge,UK"}]},{"given":"Rogier","family":"Van Dalen","sequence":"additional","affiliation":[{"name":"AI Center, Samsung,Cambridge,UK"}]},{"given":"Sourav","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"AI Center, Samsung,Cambridge,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref3","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv preprint arXiv:2106.04624"},{"issue":"333","key":"ref4","first-page":"1","article-title":"Open-source conversational AI with SpeechBrain 1.0","volume":"25","author":"Ravanelli","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref6","article-title":"NeMo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv preprint arXiv:1909.09577"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref8","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref10","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref11","first-page":"443","article-title":"Conformer-based end-to-end speech recognition with rotary position embedding","volume-title":"2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747691"},{"key":"ref13","article-title":"Moonshine: Speech recognition for live transcription and voice commands","author":"Jeffries","year":"2024","journal-title":"arXiv preprint arXiv:2410.15608"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.260"},{"key":"ref19","first-page":"30","article-title":"Spirit-lm: Interleaved spoken and written language model","volume":"13","author":"Nguyen","year":"2025","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383521"},{"key":"ref21","article-title":"Understanding the role of self attention for efficient speech recognition","volume-title":"International Conference on Learning Representations","author":"Shim"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-40"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447120"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-720"},{"key":"ref26","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"}],"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\/11434788.pdf?arnumber=11434788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:47Z","timestamp":1775192387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434788","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}