{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:01:34Z","timestamp":1780333294766,"version":"3.54.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688103","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"534-540","source":"Crossref","is-referenced-by-count":2,"title":["Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition"],"prefix":"10.1109","author":[{"given":"Felix","family":"Weninger","sequence":"first","affiliation":[{"name":"Nuance Communications,Burlington,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Gaudesi","sequence":"additional","affiliation":[{"name":"Nuance Communications,Torino,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ralf","family":"Leibold","sequence":"additional","affiliation":[{"name":"Nuance Communications,Aachen,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Gemello","sequence":"additional","affiliation":[{"name":"Nuance Communications,Torino,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Puming","family":"Zhan","sequence":"additional","affiliation":[{"name":"Nuance Communications,Burlington,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683565"},{"key":"ref32","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc of ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053455"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383621"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1337"},{"key":"ref36","first-page":"6635","article-title":"Multi-geometry spatial acoustic modeling for distant speech recognition","author":"kumatani","year":"2019","journal-title":"Proc of ICASSP"},{"key":"ref35","first-page":"6640","article-title":"Frequency domain multi-channel acoustic modeling for distant speech recognition","author":"wu","year":"2019","journal-title":"Proc of ICASSP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref11","first-page":"551","article-title":"Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard","author":"t\u00fcske","year":"2020","journal-title":"Proc of Interspeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-92"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-234"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764276"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054029"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462458"},{"key":"ref18","first-page":"2968","article-title":"Meeting transcription using asynchronous distant microphones","author":"yoshioka","year":"2019","journal-title":"Proc of Interspeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383500"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682650"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414123"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2959721"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc of ICML Workshop on Representation Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2719"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205029"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90019-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2030"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202473"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414652"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268977"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688103.pdf?arnumber=9688103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:42:22Z","timestamp":1652719342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688103","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}