{"id":"https://openalex.org/W4372260330","doi":"https://doi.org/10.1109/icassp49357.2023.10096972","title":"Improving Text-Audio Retrieval by Text-Aware Attention Pooling and Prior Matrix Revised Loss","display_name":"Improving Text-Audio Retrieval by Text-Aware Attention Pooling and Prior Matrix Revised Loss","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260330","doi":"https://doi.org/10.1109/icassp49357.2023.10096972"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5063679203","display_name":"Yifei Xin","orcid":"https://orcid.org/0000-0001-7792-6352"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Xin","raw_affiliation_strings":["Peking University,School of ECE,Shenzhen,China","School of ECE, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["Peking University,School of ECE,Shenzhen,China","School of ECE, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,School of ECE,Shenzhen,China","School of ECE, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"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/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":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9922999739646912,"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/pooling","display_name":"Pooling","score":0.8334805965423584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690314650535583},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5200112462043762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4380742013454437},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42753443121910095},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42572343349456787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4003095030784607},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14479216933250427}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8334805965423584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690314650535583},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5200112462043762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4380742013454437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42753443121910095},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42572343349456787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4003095030784607},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14479216933250427}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2706729717","https://openalex.org/W2896457183","https://openalex.org/W3005680577","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3159088493","https://openalex.org/W3197804339","https://openalex.org/W3209623075","https://openalex.org/W4210913346","https://openalex.org/W4221157007","https://openalex.org/W4224933373","https://openalex.org/W4226442948","https://openalex.org/W4282941750","https://openalex.org/W4297841486","https://openalex.org/W4312069030","https://openalex.org/W4312372711","https://openalex.org/W4385245566","https://openalex.org/W6739520758","https://openalex.org/W6739901393","https://openalex.org/W6774314701","https://openalex.org/W6780226713","https://openalex.org/W6801013943","https://openalex.org/W6807957504","https://openalex.org/W6838623770"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"In":[0,62],"text-audio":[1,117],"retrieval":[2],"(TAR)":[3],"tasks,":[4],"due":[5],"to":[6,25,51,86,88,127],"the":[7,15,20,29,35,40,46,59,99,106,112,129,146],"heterogeneity":[8],"of":[9,115],"contents":[10],"between":[11],"text":[12,21,85],"and":[13],"audio,":[14],"semantic":[16],"information":[17,55],"contained":[18],"in":[19,58],"is":[22,49,76],"only":[23,97],"similar":[24,92],"certain":[26],"frames":[27],"within":[28],"audio.":[30],"Yet,":[31],"existing":[32],"works":[33],"aggregate":[34],"entire":[36],"audio":[37,54],"without":[38],"considering":[39],"text,":[41],"such":[42],"as":[43],"mean-pooling":[44],"over":[45],"frames,":[47],"which":[48,75],"likely":[50],"encode":[52],"misleading":[53],"not":[56],"described":[57],"given":[60],"text.":[61],"this":[63],"paper,":[64],"we":[65,119],"present":[66],"a":[67,78,84,121],"text-aware":[68],"attention":[69,82],"pooling":[70,159],"(TAP)":[71],"module":[72],"for":[73,83,101],"TAR,":[74],"essentially":[77],"scaled":[79],"dot":[80],"product":[81],"attend":[87],"its":[89],"most":[90],"semantically":[91],"frames.":[93],"Furthermore,":[94],"previous":[95],"methods":[96],"conduct":[98],"softmax":[100],"every":[102],"single-side":[103],"retrieval,":[104],"ignoring":[105],"potential":[107],"cross-retrieval":[108],"information.":[109],"By":[110],"exploring":[111],"intrinsic":[113],"prior":[114,122],"each":[116],"pair,":[118],"introduce":[120],"matrix":[123],"revised":[124],"(PMR)":[125],"loss":[126,164],"filter":[128],"hard":[130],"case":[131],"with":[132],"high":[133],"(or":[134,139],"low)":[135],"text-to-audio":[136],"but":[137],"low":[138],"high)":[140],"audio-to-text":[141],"similarity":[142],"scores,":[143],"thus":[144],"achieving":[145],"dual":[147],"optimal":[148],"match.":[149],"Experiments":[150],"show":[151],"that":[152],"our":[153,162],"TAP":[154],"significantly":[155],"outperforms":[156],"various":[157],"text-agnostic":[158],"functions.":[160],"Moreover,":[161],"PMR":[163],"also":[165],"shows":[166],"stable":[167],"performance":[168],"gains":[169],"on":[170],"multiple":[171],"datasets.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}