{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:59:37Z","timestamp":1775199577070,"version":"3.50.1"},"reference-count":45,"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\/asru65441.2025.11434597","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Phoneme Overlapping-Aware Pre-Training with External Text Resources for Multi-Talker ASR"],"prefix":"10.1109","author":[{"given":"Ryo","family":"Masumura","sequence":"first","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Tomohiro","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Naoki","family":"Makishima","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Mana","family":"Ihori","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Shota","family":"Orihashi","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Naotaka","family":"Kawata","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Taiga","family":"Yamane","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Satoshi","family":"Suzuki","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]},{"given":"Takafumi","family":"Moriya","sequence":"additional","affiliation":[{"name":"NTT Inc.,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref3","article-title":"Survey of end-to-end multi-speaker automatic speech recognition for monaural audio","author":"He","year":"2025","journal-title":"arXiv preprint arXiv:2505.10975"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-305"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8682822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054029"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-999"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2988423"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832330"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2043"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-564"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446059"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-102"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094928"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446589"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-343"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1930"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415058"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414080"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-906"},{"key":"ref27","first-page":"28492","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"Proc. International conference on machine learning (ICML)","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1276"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-971"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832215"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095295"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1952"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094787"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/slt61566.2024.10832362"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887642"},{"key":"ref37","article-title":"UL2: Unifying language learning paradigms","author":"Tay","year":"2022","journal-title":"arXiv preprint arXiv:2205.05131"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref39","first-page":"947952","article-title":"Spontaneous speech corpus of Japanese","volume-title":"proc. International Conference on Language Resources and Evaluation (LREC)","author":"Maekawa"},{"key":"ref40","first-page":"4211","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proc. Conference on Language Resources and Evaluation (LREC)","author":"Ardila"},{"key":"ref41","article-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","volume-title":"arXiv preprint arXiv:1711.00354","author":"Sonobe","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Liu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"}],"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\/11434597.pdf?arnumber=11434597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:56:14Z","timestamp":1775192174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434597","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}