{"id":"https://openalex.org/W3027851323","doi":"https://doi.org/10.1109/taslp.2020.2996082","title":"Multimodal Word Discovery and Retrieval With Spoken Descriptions and Visual Concepts","display_name":"Multimodal Word Discovery and Retrieval With Spoken Descriptions and Visual Concepts","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3027851323","doi":"https://doi.org/10.1109/taslp.2020.2996082","mag":"3027851323"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2996082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2996082","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liming Wang","raw_affiliation_strings":["Electrical and Computer Engineering, University of Illinois System, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0002-5562-8386","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Illinois System, Urbana, USA","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering, University of Illinois System, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0002-5631-2893","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Illinois System, Urbana, USA","institution_ids":["https://openalex.org/I2801919071"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2708,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63235603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"28","issue":null,"first_page":"1560","last_page":"1573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.8368918895721436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6763830184936523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6207268834114075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6044102907180786},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5787862539291382},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5727769136428833},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5697404146194458},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5133706331253052},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.446407288312912},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.43869292736053467},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4127257168292999},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13030755519866943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368918895721436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6763830184936523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6207268834114075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6044102907180786},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5787862539291382},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5727769136428833},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5697404146194458},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5133706331253052},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.446407288312912},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.43869292736053467},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4127257168292999},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13030755519866943},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.2996082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2996082","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1486632395","https://openalex.org/W1905882502","https://openalex.org/W2006969979","https://openalex.org/W2016313444","https://openalex.org/W2038698865","https://openalex.org/W2063655091","https://openalex.org/W2081580037","https://openalex.org/W2100768664","https://openalex.org/W2103633133","https://openalex.org/W2112912048","https://openalex.org/W2114347655","https://openalex.org/W2117126688","https://openalex.org/W2121227244","https://openalex.org/W2133564696","https://openalex.org/W2148154194","https://openalex.org/W2156580397","https://openalex.org/W2156985047","https://openalex.org/W2185175083","https://openalex.org/W2295297373","https://openalex.org/W2347145335","https://openalex.org/W2398490608","https://openalex.org/W2466918907","https://openalex.org/W2556930864","https://openalex.org/W2568262903","https://openalex.org/W2586148577","https://openalex.org/W2671812860","https://openalex.org/W2730658205","https://openalex.org/W2743264952","https://openalex.org/W2746778230","https://openalex.org/W2808682925","https://openalex.org/W2927673779","https://openalex.org/W2950057603","https://openalex.org/W2950133079","https://openalex.org/W2962693497","https://openalex.org/W2962753610","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963620343","https://openalex.org/W2964169922","https://openalex.org/W2964308564","https://openalex.org/W2973009197","https://openalex.org/W3102219307","https://openalex.org/W6628849183","https://openalex.org/W6652311901","https://openalex.org/W6675022971","https://openalex.org/W6676047094","https://openalex.org/W6676647902","https://openalex.org/W6677461952","https://openalex.org/W6678277124","https://openalex.org/W6679434410","https://openalex.org/W6729977899","https://openalex.org/W6740930807"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2735765216","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W2153098279","https://openalex.org/W2404510748","https://openalex.org/W3089218859"],"abstract_inverted_index":{"In":[0,101],"the":[1,16,61,141,143,146,155,163,170,181],"absence":[2],"of":[3,15,18,27,45,74,77,82,180],"dictionaries,":[4],"translators,":[5],"or":[6],"grammars,":[7],"it":[8],"is":[9,60],"still":[10],"possible":[11],"to":[12,24,96],"learn":[13],"some":[14,179],"words":[17],"a":[19,34,42,56,72,80,88,150],"new":[20],"language":[21],"by":[22],"listening":[23],"spoken":[25,75,185],"descriptions":[26,76],"images.":[28],"If":[29],"several":[30],"images,":[31],"each":[32,39],"containing":[33],"particular":[35,43],"visually":[36],"salient":[37],"object,":[38],"co-occur":[40],"with":[41,131,169],"sequence":[44],"speech":[46,53],"sounds,":[47],"we":[48,165],"can":[49],"infer":[50],"that":[51],"those":[52],"sounds":[54],"are":[55,109,129],"word":[57,66,106,157,175,186],"whose":[58],"definition":[59],"visible":[62],"object.":[63],"A":[64],"multimodal":[65,105,184],"discovery":[67,107,158,176],"system":[68],"accepts,":[69],"as":[70],"input,":[71],"database":[73],"images":[78],"(or":[79,93],"set":[81],"corresponding":[83],"phone":[84,94],"transcriptions)":[85],"and":[86,119,135,177],"learns":[87],"mapping":[89],"from":[90],"waveform":[91],"segments":[92],"strings)":[95],"their":[97],"associated":[98],"image":[99],"concepts.":[100],"this":[102],"article,":[103],"four":[104],"systems":[108,128],"demonstrated:":[110],"three":[111],"models":[112,168],"based":[113,121],"on":[114,122,160],"statistical":[115],"machine":[116,124],"translation":[117,125],"(SMT)":[118],"one":[120],"neural":[123],"(NMT).":[126],"The":[127],"trained":[130],"phonetic":[132],"transcriptions,":[133],"MFCC":[134],"multilingual":[136],"bottleneck":[137],"features":[138],"(MBN).":[139],"On":[140,162],"phone-level,":[142],"SMT":[144],"outperforms":[145],"NMT":[147],"model,":[148],"achieving":[149],"61.6%":[151],"F1":[152],"score":[153],"in":[154,183],"phone-level":[156],"task":[159],"Flickr30k.":[161],"audio-level,":[164],"compared":[166],"our":[167],"existing":[171],"ES-KMeans":[172],"algorithm":[173],"for":[174],"present":[178],"challenges":[182],"discovery.":[187]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}