{"id":"https://openalex.org/W3161204797","doi":"https://doi.org/10.1109/icassp39728.2021.9414418","title":"Align or attend? Toward More Efficient and Accurate Spoken Word Discovery Using Speech-to-Image Retrieval","display_name":"Align or attend? Toward More Efficient and Accurate Spoken Word Discovery Using Speech-to-Image Retrieval","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161204797","doi":"https://doi.org/10.1109/icassp39728.2021.9414418","mag":"3161204797"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058722770","display_name":"Liming Wang","orcid":"https://orcid.org/0000-0002-5562-8386"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liming Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021472684","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0003-1826-7419"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CN","NL"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology","School of Software Engineering, Xi\u2019an Jiaotong University","School of Software Engineering, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1643,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80334188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"19","issue":null,"first_page":"7603","last_page":"7607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8318837881088257},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7697514295578003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6339707374572754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5687374472618103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5542101263999939},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49741891026496887},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4877091348171234},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4695734679698944},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4318796992301941},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07832178473472595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318837881088257},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7697514295578003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6339707374572754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5687374472618103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5542101263999939},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49741891026496887},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4877091348171234},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4695734679698944},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4318796992301941},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07832178473472595},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2006969979","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2119775030","https://openalex.org/W2122228338","https://openalex.org/W2133564696","https://openalex.org/W2137010615","https://openalex.org/W2148154194","https://openalex.org/W2277195237","https://openalex.org/W2398490608","https://openalex.org/W2556930864","https://openalex.org/W2613718673","https://openalex.org/W2736876693","https://openalex.org/W2745461083","https://openalex.org/W2752796333","https://openalex.org/W2796315435","https://openalex.org/W2920166246","https://openalex.org/W2950133079","https://openalex.org/W2962780374","https://openalex.org/W2962832640","https://openalex.org/W2962862718","https://openalex.org/W2963403868","https://openalex.org/W2963799213","https://openalex.org/W2963902314","https://openalex.org/W2963966654","https://openalex.org/W2964308564","https://openalex.org/W2971709506","https://openalex.org/W2988907666","https://openalex.org/W2995680346","https://openalex.org/W3095293218","https://openalex.org/W3102219307","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6652311901","https://openalex.org/W6676647902","https://openalex.org/W6679434410","https://openalex.org/W6680628865","https://openalex.org/W6712720595","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6770596778"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2947282851","https://openalex.org/W2184288218","https://openalex.org/W2071180033","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W155590726","https://openalex.org/W2147874738","https://openalex.org/W2528082075"],"abstract_inverted_index":{"Multimodal":[0],"word":[1,45,65],"discovery":[2,46,66],"(MWD)":[3],"is":[4,26],"often":[5],"treated":[6],"as":[7],"a":[8,29,74],"byproduct":[9],"of":[10,23,73],"the":[11],"speech-to-image":[12],"retrieval":[13,43,77],"problem.":[14],"However,":[15],"our":[16,39],"theoretical":[17],"analysis":[18],"shows":[19],"that":[20,55,68],"some":[21],"kind":[22],"alignment/attention":[24],"mechanism":[25],"crucial":[27],"for":[28],"MWD":[30],"system":[31],"to":[32,71],"learn":[33],"meaningful":[34],"word-level":[35],"representation.":[36],"We":[37],"verify":[38],"theory":[40],"by":[41,81],"conducting":[42],"and":[44,50,52,61,83],"experiments":[47],"on":[48],"MSCOCO":[49],"Flickr8k,":[51],"empirically":[53],"demonstrate":[54],"both":[56],"neural":[57,76],"MT":[58,63],"with":[59],"self-attention":[60],"statistical":[62],"achieve":[64],"scores":[67,87],"are":[69],"superior":[70],"those":[72],"state-of-the-art":[75],"system,":[78],"outperforming":[79],"it":[80],"2%":[82],"5%":[84],"alignment":[85],"F1":[86],"respectively.":[88]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}