{"id":"https://openalex.org/W4283767777","doi":"https://doi.org/10.21437/interspeech.2022-580","title":"Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting","display_name":"Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283767777","doi":"https://doi.org/10.21437/interspeech.2022-580"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-580","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5034308292","display_name":"Hyeon-Kyeong Shin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyeon-Kyeong Shin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075891585","display_name":"Hye-Won Han","orcid":"https://orcid.org/0000-0001-6620-8283"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyewon Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652838","display_name":"Doyeon Kim","orcid":"https://orcid.org/0000-0003-3717-7275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doyeon Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046276512","display_name":"Soo-Whan Chung","orcid":"https://orcid.org/0000-0001-6529-2196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soo-Whan Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7839,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92980799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1871","last_page":"1875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/spotting","display_name":"Spotting","score":0.8864762187004089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8139011859893799},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8015083074569702},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6100088357925415},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6008209586143494},{"id":"https://openalex.org/keywords/agreement","display_name":"Agreement","score":0.5481451153755188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48323139548301697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.446042001247406},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1529034972190857}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8864762187004089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139011859893799},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8015083074569702},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6100088357925415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6008209586143494},{"id":"https://openalex.org/C2776818064","wikidata":"https://www.wikidata.org/wiki/Q829903","display_name":"Agreement","level":2,"score":0.5481451153755188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48323139548301697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.446042001247406},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1529034972190857},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-580","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2742860341","https://openalex.org/W2559372442","https://openalex.org/W4248007934","https://openalex.org/W3018114492","https://openalex.org/W1483316057","https://openalex.org/W1554833030","https://openalex.org/W2323788589","https://openalex.org/W3107474891","https://openalex.org/W2171506966","https://openalex.org/W2546648789"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,52,92],"propose":[4],"a":[5,48,77,97],"novel":[6],"end-to-end":[7,64],"user-defined":[8],"keyword":[9,27,38,71,107],"spotting":[10,108],"method":[11,30,112],"that":[12,59],"utilizes":[13],"linguistically":[14],"corresponding":[15],"patterns":[16],"between":[17],"speech":[18,26],"and":[19,44,70,124],"text":[20,37,45],"sequences.":[21],"Unlike":[22],"previous":[23],"approaches":[24],"requiring":[25],"enrollment,":[28],"our":[29],"compares":[31],"input":[32],"queries":[33],"with":[34,66],"an":[35,54,63],"enrolled":[36],"sequence.":[39],"To":[40],"place":[41],"the":[42,81,94],"audio":[43],"representations":[46],"within":[47],"common":[49],"latent":[50],"space,":[51],"adopt":[53],"attention-based":[55],"cross-modal":[56,125],"matching":[57,68],"approach":[58],"is":[60],"trained":[61],"in":[62,88],"manner":[65],"monotonic":[67],"loss":[69,79],"classification":[72],"loss.":[73],"We":[74],"also":[75],"utilize":[76],"de-noising":[78],"for":[80,104],"acoustic":[82],"embedding":[83],"network":[84],"to":[85,121],"improve":[86],"robustness":[87],"noisy":[89],"environments.":[90],"Additionally,":[91],"introduce":[93],"LibriPhrase":[95],"dataset,":[96],"new":[98],"short-phrase":[99],"dataset":[100],"based":[101],"on":[102,116],"LibriSpeech":[103],"efficiently":[105],"training":[106],"models.":[109],"Our":[110],"proposed":[111],"achieves":[113],"competitive":[114],"results":[115],"various":[117],"evaluation":[118],"sets":[119],"compared":[120],"other":[122],"single-modal":[123],"baselines.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}