{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:52Z","timestamp":1775229772536,"version":"3.50.1"},"reference-count":36,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448210","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12476-12480","source":"Crossref","is-referenced-by-count":4,"title":["SpeechDPR: End-To-End Spoken Passage Retrieval For Open-Domain Spoken Question Answering"],"prefix":"10.1109","author":[{"given":"Chyi-Jiunn","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University"}]},{"given":"Guan-Ting","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Yung-Sung","family":"Chuang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}]},{"given":"Wei-Lun","family":"Wu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Shang-Wen","family":"Li","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Rembrand"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Lin-Shan","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-04447-2_36","article-title":"Overview of QAST 2008","volume-title":"Workshop of the Cross-Language Evaluation Forum for European Languages","author":"Turmo"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2328967.2328972"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1714"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639505"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-4013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref8","article-title":"Unsupervised speech recognition","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1570"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.152"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-612","article-title":"DUAL: Textless Spoken Question Answering with Speech Discrete Unit Adaptive Learning","author":"Lin","year":"2022"},{"key":"ref13","article-title":"On Generative Spoken Language Modeling from Raw Audio","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"ref16","article-title":"The TREC Spoken Document Retrieval Track: A Success Story","author":"Garofolo","year":"2000","journal-title":"NIST SPECIAL PUBLICATION SP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/1500000020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.917992"},{"key":"ref19","article-title":"Speech recognition and information retrieval: Experiments in retrieving spoken documents","volume-title":"Proceedings of the DARPA speech recognition workshop","author":"Witbrock"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2988788"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462570"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462396"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2018.2872106","article-title":"Semantic speech retrieval with a visually grounded model of untranscribed speech","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition workshops","author":"Kamper"},{"key":"ref24","article-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","volume-title":"International Conference on Learning Representations","author":"Xiong"},{"key":"ref25","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.189"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.496"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-017-9410-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1264"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref32","article-title":"Semantic parsing on freebase from question-answer pairs","volume-title":"Proceedings of the 2013 conference on empirical methods in natural language processing","author":"Berant"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24027-5_20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref35","article-title":"DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION","volume-title":"International Conference on Learning Representations","author":"He"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"}],"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\/10448210.pdf?arnumber=10448210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:31:43Z","timestamp":1722573103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448210","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}