{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:33:44Z","timestamp":1730230424233,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414418","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7603-7607","source":"Crossref","is-referenced-by-count":4,"title":["Align or attend? Toward More Efficient and Accurate Spoken Word Discovery Using Speech-to-Image Retrieval"],"prefix":"10.1109","author":[{"given":"Liming","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinsheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"31st Conference on Neural Information Processing Systems (NIPS 2017)"},{"key":"ref11","first-page":"263","article-title":"The mathematics of statistical machine translation: parameter estimation","volume":"19","author":"brown","year":"1993","journal-title":"Computational Linguistics"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1148"},{"key":"ref14","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref15","article-title":"Unsupervised word discovery from speech using automatic segmentation into syllable-like units","author":"rasanen","year":"2015","journal-title":"InterSpeech"},{"key":"ref16","article-title":"Collecting image annotations using Amazon’s mechanical turk","author":"rashtchian","year":"2010","journal-title":"Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk"},{"key":"ref17","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref18","article-title":"Deep multimodal semantic embed-dings for speech and images","author":"harwath","year":"2015","journal-title":"Proc Automatic Speech Recognition and Understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/GLU.2017-9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220260"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01231-1_40","article-title":"Jointly discovering visual objects and spoken words from raw sensory input","author":"harwath","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref3","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3067"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683069"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872106"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1006"},{"key":"ref2","article-title":"The role of sensorimotor function, associative memory and reinforcement learning in automatic acquisition of spoken language by an autonomous robot","author":"levinson","year":"2000","journal-title":"Joint NSF DARPA Workshop on Development and Learning"},{"key":"ref9","article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","author":"harwath","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref1","first-page":"1","article-title":"A computational model of word learning from multi-modal sensory input","author":"roy","year":"2000","journal-title":"Proceedings of the international conference of cognitive modeling"},{"key":"ref20","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref21","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems 28 (NIPS 2015)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414418.pdf?arnumber=9414418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:09Z","timestamp":1652197269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414418","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}