{"id":"https://openalex.org/W4408355690","doi":"https://doi.org/10.1109/icassp49660.2025.10890820","title":"Enhancing Unsupervised Acoustic Word Embedding with Visual-Grounded Speech Model and Novel Word-level ABX Evaluation Schemes","display_name":"Enhancing Unsupervised Acoustic Word Embedding with Visual-Grounded Speech Model and Novel Word-level ABX Evaluation Schemes","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355690","doi":"https://doi.org/10.1109/icassp49660.2025.10890820"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":null,"display_name":"Mau Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mau Nguyen","raw_affiliation_strings":["JAIST,School of Information Science,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"JAIST,School of Information Science,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014332130","display_name":"Shinobu Hasegawa","orcid":"https://orcid.org/0000-0002-0892-9629"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinobu Hasegawa","raw_affiliation_strings":["JAIST,Center of IDER,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"JAIST,Center of IDER,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["NAIST,School of Information Science,Ikoma,Japan"],"affiliations":[{"raw_affiliation_string":"NAIST,School of Information Science,Ikoma,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01838865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9661999940872192,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9661999940872192,"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/abx-test","display_name":"ABX test","score":0.8549520969390869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7693902254104614},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6692421436309814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6692022681236267},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5888932943344116},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5120239853858948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4701911211013794},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3899552822113037},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16668719053268433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08028349280357361}],"concepts":[{"id":"https://openalex.org/C60962613","wikidata":"https://www.wikidata.org/wiki/Q287654","display_name":"ABX test","level":2,"score":0.8549520969390869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693902254104614},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6692421436309814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6692022681236267},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5888932943344116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5120239853858948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4701911211013794},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3899552822113037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16668719053268433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08028349280357361},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2033178790","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2112716658","https://openalex.org/W2128160875","https://openalex.org/W2145410271","https://openalex.org/W2156972453","https://openalex.org/W2295297373","https://openalex.org/W2395899413","https://openalex.org/W2586148577","https://openalex.org/W2909431601","https://openalex.org/W2940544976","https://openalex.org/W2963720603","https://openalex.org/W3044967013","https://openalex.org/W3200287550","https://openalex.org/W3209059054","https://openalex.org/W4224875474","https://openalex.org/W6600593648","https://openalex.org/W6731763572"],"related_works":["https://openalex.org/W947140380","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255","https://openalex.org/W4287599800","https://openalex.org/W4385432812"],"abstract_inverted_index":{"Most":[0],"recent":[1],"Acoustic":[2],"Word":[3],"Embedding":[4],"(AWE)":[5],"systems":[6],"utilize":[7],"an":[8,59],"autoencoder-like":[9],"approach":[10,61,113],"to":[11,62,118,140],"compress":[12],"speech":[13],"features":[14],"of":[15,104],"arbitrary":[16],"shapes":[17],"into":[18],"fixed-size":[19],"numerical":[20],"vectors":[21],"and":[22,101,130],"then":[23],"reconstructing":[24],"it,":[25],"thereby":[26],"capturing":[27],"essential":[28],"patterns":[29],"in":[30,120],"the":[31,72,91,115],"data.":[32,79],"Unfortunately,":[33],"AWE":[34,116],"models":[35],"have":[36,47],"commonly":[37],"relied":[38],"on":[39,127],"supervised":[40],"learning,":[41],"necessitating":[42],"extensive":[43],"textual":[44,78],"data,":[45],"or":[46,77],"employed":[48],"unsupervised":[49,60,123],"dynamic-based":[50,133],"methods":[51],"that":[52,88,110],"are":[53],"computationally":[54,131],"demanding.":[55],"This":[56],"paper":[57],"introduces":[58],"AWE,":[63],"leveraging":[64],"a":[65,83,98,121],"self-supervised":[66],"Visual-Grounded":[67],"Speech":[68],"(VGS)":[69],"model,":[70],"eliminating":[71],"need":[73],"for":[74],"dynamic":[75],"algorithms":[76],"Additionally,":[80],"we":[81],"propose":[82],"fine-grained":[84],"ABX":[85],"evaluation":[86,103],"protocol":[87],"meticulously":[89],"assesses":[90],"acoustic":[92],"similarity":[93],"between":[94],"spoken":[95],"segments,":[96],"providing":[97],"more":[99],"comprehensive":[100],"fair":[102],"model":[105,117],"performance.":[106],"Our":[107],"findings":[108],"indicate":[109],"proposed":[111],"visual-grounded":[112],"allows":[114],"function":[119],"truly":[122],"manner":[124],"without":[125],"relying":[126],"text":[128],"data":[129],"intensive":[132],"algorithms,":[134],"while":[135],"also":[136],"achieving":[137],"performance":[138],"comparable":[139],"other":[141],"approaches.":[142]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}