{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:31Z","timestamp":1776885511866,"version":"3.51.2"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389679","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["Transformer Attractors for Robust and Efficient End-To-End Neural Diarization"],"prefix":"10.1109","author":[{"given":"Lahiru","family":"Samarakoon","sequence":"first","affiliation":[{"name":"Fano Labs,Hong Kong"}]},{"given":"Samuel J","family":"Broughton","sequence":"additional","affiliation":[{"name":"Fano Labs,Hong Kong"}]},{"given":"Marc","family":"H\u00e4rk\u00f6nen","sequence":"additional","affiliation":[{"name":"Fano Labs,Hong Kong"}]},{"given":"Ivan","family":"Fung","sequence":"additional","affiliation":[{"name":"Fano Labs,Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1377"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094824"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687875"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383523"},{"key":"ref15","article-title":"Towards end-to-end speaker diarization in the wild","author":"Pan","year":"2022","journal-title":"arXiv preprint arXiv:2211.01299"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2401"},{"key":"ref18","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Vaswani"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref20","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI"},{"issue":"1","key":"ref21","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref23","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref25","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning. PMLR","author":"Radford"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10169"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022924"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746602"},{"key":"ref29","article-title":"The Hitachi-JHU DIHARD III system: Competitive end-to-end neural diarization and x-vector clustering systems combined by DOVER-Lap","author":"Horiguchi","year":"2021","journal-title":"arXiv preprint arXiv:2102.01363"},{"key":"ref30","volume-title":"End-to-end speaker diarization system for the third DIHARD challenge system description","author":"Leung","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1249"},{"key":"ref33","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","article-title":"Third DIHARD challenge evaluation plan","author":"Ryant","year":"2020","journal-title":"arXiv preprint arXiv:2006.05815"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-729"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","volume-title":"3rd International Conference on Learning Representations, Conference Track Proceedings","author":"Kingma"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389679.pdf?arnumber=10389679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:34Z","timestamp":1706028154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389679","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}