{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:11Z","timestamp":1764400571540,"version":"3.46.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249056","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"7-12","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Dual-Mode Training for Real-Time Target Speaker Extraction"],"prefix":"10.1109","author":[{"given":"Li","family":"Li","sequence":"first","affiliation":[{"name":"CyberAgent,AI Lab,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shogo","family":"Seki","sequence":"additional","affiliation":[{"name":"CyberAgent,AI Lab,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2023.3240008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1250\/ast.e24.124"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414998"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref5","first-page":"2728","article-title":"VoiceFilter: Targeted Voice Separation by SpeakerConditioned Spectrogram Masking","volume-title":"in Proc. INTERSPEECH","author":"Muckenhirn","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2266"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-218"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1513"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3527766"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1193"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10962"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642057"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-413"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref17","article-title":"Distilling the knowledge in a neural network","volume-title":"in NIPS Deep Learning and Representation Learning Workshop","author":"Hinton","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref19","article-title":"Dual-mode asr: Unify and improve streaming asr with full-context modeling","volume-title":"ICLR 2021, ICLR 2021","author":"Yu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096724"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746678"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2010.5495701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249056.pdf?arnumber=11249056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:12:25Z","timestamp":1764400345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249056","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}