{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:15:54Z","timestamp":1773155754804,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446337","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1001-1005","source":"Crossref","is-referenced-by-count":15,"title":["An Empirical Study on the Impact of Positional Encoding in Transformer-Based Monaural Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Qiquan","family":"Zhang","sequence":"first","affiliation":[{"name":"University of New South,School of Electrical Engineering and Telecommunications,Wales,Australia"}]},{"given":"Meng","family":"Ge","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Hongxu","family":"Zhu","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Eliathamby","family":"Ambikairajah","sequence":"additional","affiliation":[{"name":"University of New South,School of Electrical Engineering and Telecommunications,Wales,Australia"}]},{"given":"Qi","family":"Song","sequence":"additional","affiliation":[{"name":"Alibaba Group,China"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta,United States"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1446"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2019.01.019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923680"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2019.2955276"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2015.2512042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref16","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987441"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746454"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2995273"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-46"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10781"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3225649"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096693"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2526"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.10.004"},{"key":"ref27","first-page":"455","article-title":"Boosting objective scores of a speech enhancement model by metric-gan post-processing","author":"Fu","year":"2020","journal-title":"APSIPA ASC"},{"issue":"140","key":"ref28","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","first-page":"8386","article-title":"Kerple: Kernelized relative positional embedding for length extrapolation","volume-title":"Proc. NeurIPS","volume":"35","author":"Chi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref34","first-page":"1988","article-title":"Description of the RSG-10 noise database","volume":"3","author":"Steeneken","year":"1988","journal-title":"report IZF"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7590807"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472068"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-774"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041110"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref41","article-title":"Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","author":"Recommendation","year":"2001","journal-title":"Rec. ITU-T P. 862"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446337.pdf?arnumber=10446337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:38:41Z","timestamp":1722573521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446337","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}