{"id":"https://openalex.org/W4410341965","doi":"https://doi.org/10.1109/ncc63735.2025.10983304","title":"Duration-Aware Phone Embedding Upsampling for Open Vocabulary Keyword Spotting","display_name":"Duration-Aware Phone Embedding Upsampling for Open Vocabulary Keyword Spotting","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4410341965","doi":"https://doi.org/10.1109/ncc63735.2025.10983304"},"language":"en","primary_location":{"id":"doi:10.1109/ncc63735.2025.10983304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","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,Speech Information Processing Lab,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Speech Information Processing Lab,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095085122","display_name":"Naveen Doppa","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":"Naveen Doppa","raw_affiliation_strings":["Indian Institute of Technology,Speech Information Processing Lab,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Speech Information Processing Lab,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023195061","display_name":"Sri Rama Murty K","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":"Sri Rama Murty K","raw_affiliation_strings":["Indian Institute of Technology,Speech Information Processing Lab,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Speech Information Processing Lab,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":0.05194348,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9873999953269958,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9873999953269958,"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/T12031","display_name":"Speech and dialogue systems","score":0.9779000282287598,"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/T10028","display_name":"Topic Modeling","score":0.968999981880188,"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":0.9306204319000244},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.8886698484420776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7094722390174866},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6268942356109619},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6199706792831421},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5949532985687256},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.525322675704956},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4625505805015564},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4327154755592346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38187894225120544},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06561601161956787},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06158098578453064},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.04956534504890442}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9306204319000244},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8886698484420776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094722390174866},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6268942356109619},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6199706792831421},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5949532985687256},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.525322675704956},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4625505805015564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4327154755592346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38187894225120544},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06561601161956787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06158098578453064},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.04956534504890442},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc63735.2025.10983304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1553469512","https://openalex.org/W2034940213","https://openalex.org/W2074671152","https://openalex.org/W2125838338","https://openalex.org/W2293829681","https://openalex.org/W2407023693","https://openalex.org/W2510945575","https://openalex.org/W2578392894","https://openalex.org/W2697044473","https://openalex.org/W2962707338","https://openalex.org/W2962766617","https://openalex.org/W2963609956","https://openalex.org/W2964187693","https://openalex.org/W2972613398","https://openalex.org/W3097777922","https://openalex.org/W3162022030","https://openalex.org/W3196482042","https://openalex.org/W4283767777","https://openalex.org/W4385489560","https://openalex.org/W4385822437","https://openalex.org/W4385823483","https://openalex.org/W4392904395","https://openalex.org/W4393973541","https://openalex.org/W6631362777","https://openalex.org/W6640212811","https://openalex.org/W6774097463","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4408353962","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539"],"abstract_inverted_index":{"Open":[0],"Vocabulary":[1],"Keyword":[2],"Spotting":[3],"(KWS)":[4],"gained":[5],"significant":[6],"interest":[7],"due":[8],"to":[9,12,23,28,73,143],"the":[10,42,77,93,130,138,149,168,171,175,191],"ability":[11],"detect":[13],"custom":[14],"keywords.":[15],"Still,":[16,52],"it":[17,26],"is":[18],"a":[19,84,118,162],"very":[20],"challenging":[21],"field":[22],"develop,":[24],"as":[25,57],"has":[27],"overcome":[29],"domain":[30,38,201],"mismatch":[31,39,59],"and":[32,44,63,71,107,112,133,174,193,202],"rate":[33,58,146,203],"mismatch.":[34],"Existing":[35],"methods":[36],"solve":[37],"by":[40],"bringing":[41],"acoustic":[43,111,145,158],"text":[45,64,113],"keyword":[46,65,89],"embeddings":[47,132,142,155,160],"into":[48,117],"shared":[49,119],"latent":[50,120],"space.":[51],"they":[53],"face":[54],"challenges":[55,197],"such":[56],"where":[60],"speech":[61],"frames":[62],"phonemes":[66],"have":[67],"different":[68],"temporal":[69],"resolutions,":[70],"struggle":[72],"find":[74],"agreement":[75],"between":[76],"modalities.":[78],"To":[79],"address":[80],"these,":[81],"we":[82],"propose":[83],"method":[85],"for":[86],"open":[87],"vocabulary":[88],"spotting":[90],"that":[91,184],"matches":[92],"rate.":[94],"It":[95],"consists":[96],"of":[97],"an":[98,144],"Acoustic":[99],"encoder,":[100,102],"Text":[101],"Duration":[103],"estimator,":[104],"Upsampler,":[105],"Localizer,":[106],"Detector":[108],"modules.":[109],"The":[110,126,152],"encoders":[114],"map":[115],"inputs":[116],"space,":[121],"enabling":[122],"effective":[123],"cross-modal":[124],"representation.":[125],"duration":[127],"estimator":[128],"takes":[129],"phoneme":[131],"predicts":[134,177],"their":[135],"durations.":[136,151],"Then":[137],"Upsampler":[139],"interpolates":[140],"these":[141],"based":[147],"on":[148],"predicted":[150],"resultant":[153],"upsampled":[154],"aligned":[156],"with":[157],"frame":[159],"using":[161],"multi-head":[163],"cross-attention":[164],"mechanism.":[165],"Following":[166],"this,":[167],"localizer":[169],"identifies":[170],"keyword's":[172],"location,":[173],"detector":[176],"its":[178],"existence.":[179],"Our":[180],"experimental":[181],"results":[182],"demonstrate":[183],"this":[185],"approach":[186],"performs":[187],"significantly":[188],"better":[189],"than":[190],"baseline":[192],"effectively":[194],"addresses":[195],"key":[196],"in":[198],"KWS,":[199],"including":[200],"mismatches.":[204]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}