{"id":"https://openalex.org/W7148470286","doi":"https://doi.org/10.1109/asru65441.2025.11434681","title":"Joint Multimodal Contrastive Learning for Robust Spoken Term Detection and Keyword Spotting","display_name":"Joint Multimodal Contrastive Learning for Robust Spoken Term Detection and Keyword Spotting","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148470286","doi":"https://doi.org/10.1109/asru65441.2025.11434681"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5104108496","display_name":"Ramesh Gundluru","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ramesh Gundluru","raw_affiliation_strings":["Indian Institute of Technology,Electrical Engineering,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Electrical Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129864310","display_name":"Shubham Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shubham Gupta","raw_affiliation_strings":["Indian Institute of Technology,Artificial Intelligence,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Artificial Intelligence,Hyderabad,India","institution_ids":["https://openalex.org/I65181880","https://openalex.org/I4210146682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132804749","display_name":"K Sri Rama Murty","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K Sri Rama Murty","raw_affiliation_strings":["Indian Institute of Technology,Electrical Engineering,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Electrical Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104108496"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87569716,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7799000144004822,"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":0.7799000144004822,"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":0.120899997651577,"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/T12031","display_name":"Speech and dialogue systems","score":0.027699999511241913,"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/keyword-spotting","display_name":"Keyword spotting","score":0.7825999855995178},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6593000292778015},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.573199987411499},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5353999733924866},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5309000015258789},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4088999927043915},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.3978999853134155},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270000219345093},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7825999855995178},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6593000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5981000065803528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5809999704360962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5733000040054321},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.573199987411499},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3725000023841858},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6144959330558777,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W1967924372","https://openalex.org/W1984076147","https://openalex.org/W2100799972","https://openalex.org/W2128160875","https://openalex.org/W2157331557","https://openalex.org/W2747874407","https://openalex.org/W2786784963","https://openalex.org/W2888951652","https://openalex.org/W2962736743","https://openalex.org/W2962980711","https://openalex.org/W2963571336","https://openalex.org/W2963720603","https://openalex.org/W2978114332","https://openalex.org/W3131709275","https://openalex.org/W3160452051"],"related_works":[],"abstract_inverted_index":{"Acoustic":[0],"Word":[1,93],"Embeddings":[2],"(AWEs)":[3],"improve":[4],"the":[5,38,77,127],"efficiency":[6],"of":[7,32,131],"speech":[8],"retrieval":[9],"tasks":[10],"such":[11],"as":[12],"Spoken":[13],"Term":[14],"Detection":[15],"(STD)":[16],"and":[17,34,37,59,83,86,101,120],"Keyword":[18],"Spotting":[19],"(KWS).":[20],"However,":[21],"existing":[22,108],"approaches":[23],"suffer":[24],"from":[25],"limitations,":[26],"including":[27],"unimodal":[28],"supervision,":[29],"disjoint":[30],"optimization":[31],"audio-audio":[33,88],"audio-text":[35,72],"alignment,":[36],"need":[39],"for":[40],"task-specific":[41],"models.":[42],"To":[43,122],"address":[44],"these":[45],"shortcomings,":[46],"we":[47],"propose":[48],"a":[49,63],"joint":[50],"multimodal":[51],"contrastive":[52,73,89],"learning":[53],"framework":[54],"that":[55],"unifies":[56],"both":[57,118],"acoustic":[58],"cross-modal":[60],"supervision":[61],"in":[62],"shared":[64],"embedding":[65],"space.":[66],"Our":[67],"approach":[68,130],"simultaneously":[69],"optimizes:":[70],"(i)":[71],"learning,":[74,90],"inspired":[75],"by":[76],"CLAP":[78],"loss,":[79,96],"to":[80,97],"align":[81],"audio":[82],"text":[84],"representations":[85],"(ii)":[87],"via":[91],"Deep":[92],"Discrimination":[94],"(DWD)":[95],"enhance":[98],"intra-class":[99],"compactness":[100],"inter-class":[102],"separation.":[103],"The":[104],"proposed":[105],"method":[106],"outperforms":[107],"AWE":[109],"baselines":[110],"on":[111],"word":[112],"discrimination":[113],"task":[114],"while":[115],"flexibly":[116],"supporting":[117],"STD":[119],"KWS.":[121],"our":[123],"knowledge,":[124],"this":[125],"is":[126],"first":[128],"comprehensive":[129],"its":[132],"kind.":[133]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}