{"id":"https://openalex.org/W2940092410","doi":"https://doi.org/10.1109/icassp.2019.8682632","title":"Cross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio","display_name":"Cross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940092410","doi":"https://doi.org/10.1109/icassp.2019.8682632","mag":"2940092410"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073250019","display_name":"Benjamin Elizalde","orcid":"https://orcid.org/0000-0001-6461-5790"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benjamin Elizalde","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084618329","display_name":"Shuayb Zarar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuayb Zarar","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9699,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.96368964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4095","last_page":"4099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8283237218856812},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5889726877212524},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5570764541625977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4887842833995819},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.47024431824684143},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4585549235343933},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.457872599363327},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.45055603981018066},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44006410241127014},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.42848819494247437},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42127513885498047},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4206874370574951},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3996926546096802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3923954963684082},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.23316454887390137},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16969767212867737},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1324840784072876},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.10692888498306274},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08678027987480164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283237218856812},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5889726877212524},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5570764541625977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4887842833995819},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.47024431824684143},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4585549235343933},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.457872599363327},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.45055603981018066},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44006410241127014},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.42848819494247437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42127513885498047},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4206874370574951},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3996926546096802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3923954963684082},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.23316454887390137},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16969767212867737},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1324840784072876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.10692888498306274},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08678027987480164},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2010486494","https://openalex.org/W2085662862","https://openalex.org/W2087193308","https://openalex.org/W2101234009","https://openalex.org/W2138621090","https://openalex.org/W2141739745","https://openalex.org/W2154016477","https://openalex.org/W2160471965","https://openalex.org/W2250539671","https://openalex.org/W2471278348","https://openalex.org/W2606965845","https://openalex.org/W2623327532","https://openalex.org/W2770119437","https://openalex.org/W2775505379","https://openalex.org/W2783973932","https://openalex.org/W2798579254","https://openalex.org/W2913969639","https://openalex.org/W2915649242","https://openalex.org/W2963389687","https://openalex.org/W2964287480","https://openalex.org/W4294576248","https://openalex.org/W4297690166","https://openalex.org/W6675354045","https://openalex.org/W6680272447","https://openalex.org/W6736727294","https://openalex.org/W6738806211","https://openalex.org/W6746278845","https://openalex.org/W6747331233","https://openalex.org/W6748069790","https://openalex.org/W6750883802"],"related_works":["https://openalex.org/W2131156500","https://openalex.org/W2118916824","https://openalex.org/W1479881079","https://openalex.org/W1611900921","https://openalex.org/W2112616324","https://openalex.org/W2064012922","https://openalex.org/W2106826515","https://openalex.org/W2717715803","https://openalex.org/W2056936702","https://openalex.org/W4229926342"],"abstract_inverted_index":{"Existing":[0],"audio":[1,29,34,42,53,61,106,154,169],"search":[2,157,170],"engines":[3],"use":[4,149],"one":[5],"of":[6,28,58,150,175],"two":[7,68],"approaches:":[8],"matching":[9],"text-text":[10],"or":[11,36,153],"audio-audio":[12],"pairs.":[13],"In":[14],"the":[15,40,67,148],"former,":[16],"text":[17,59,152],"queries":[18,155],"are":[19,44,102],"matched":[20],"to":[21,31,47,156],"semantically":[22],"similar":[23],"words":[24],"in":[25,39,76,83,104],"an":[26,52],"index":[27],"metadata":[30],"retrieve":[32,48,159],"corresponding":[33],"clips":[35],"segments,":[37],"while":[38],"latter,":[41],"signals":[43],"directly":[45],"used":[46],"acoustically-similar":[49],"recordings":[50],"from":[51,124,131],"database.":[54],"However,":[55],"independent":[56,89],"treatment":[57],"and":[60,85,107,138,146,158,172],"has":[62],"precluded":[63],"information":[64],"exchange":[65],"between":[66],"modalities.":[69],"This":[70],"is":[71],"a":[72,118,125,167],"problem":[73],"because":[74],"similarity":[75,82],"language":[77],"does":[78],"not":[79],"always":[80],"imply":[81],"acoustics,":[84],"vice":[86],"versa.":[87],"Moreover,":[88],"modeling":[90],"can":[91,134],"be":[92,135],"error":[93],"prone":[94],"especially":[95],"for":[96,166],"ad":[97],"hoc,":[98],"user-generated":[99],"recordings,":[100],"which":[101],"noisy":[103],"both":[105],"their":[108],"associated":[109],"textual":[110],"labels.":[111],"To":[112],"overcome":[113],"this":[114],"limitation,":[115],"we":[116,142],"propose":[117],"framework":[119],"that":[120],"learns":[121],"joint":[122],"embeddings":[123],"shared":[126],"lexico-acoustic":[127,176],"space,":[128],"where":[129],"vectors":[130],"either":[132,151],"modality":[133],"mapped":[136],"together":[137],"compared":[139],"directly.":[140],"Thus,":[141],"improve":[143],"semantic":[144],"knowledge":[145],"enable":[147],"audio.":[160],"Our":[161],"results":[162],"break":[163],"new":[164],"ground":[165],"cross-modal":[168],"engine,":[171],"further":[173],"exploration":[174],"spaces.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}