{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T12:21:13Z","timestamp":1753359673865,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023097","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"108-114","source":"Crossref","is-referenced-by-count":1,"title":["Untied Positional Encodings for Efficient Transformer-Based Speech Recognition"],"prefix":"10.1109","author":[{"given":"Lahiru","family":"Samarakoon","sequence":"first","affiliation":[{"name":"Fano Labs,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Fung","sequence":"additional","affiliation":[{"name":"Fano Labs,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Rethinking attention with performers","author":"Choromanski","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref11","article-title":"Transformers with convolutional context for asr","author":"Mohamed","year":"2019","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Rethinking positional encoding in language pre-training","author":"Ke","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"6327","article-title":"Learning to encode position for transformer with continuous dynamical model","volume-title":"International Conference on Machine Learning. PMLR","author":"Liu","year":"2020"},{"key":"ref15","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","author":"He","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Da-transformer: Distance-aware transformer","author":"Wu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747691"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.465"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref22","article-title":"Music transformer: Generating music with long-term structure","author":"Huang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414941"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1525"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.02762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","article-title":"Music transformer","author":"Huang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2404"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023097.pdf?arnumber=10023097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T09:25:08Z","timestamp":1707816308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023097","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}