{"id":"https://openalex.org/W4408355055","doi":"https://doi.org/10.1109/icassp49660.2025.10888312","title":"Phoneme-Level Contrastive Learning for User-Defined Keyword Spotting with Flexible Enrollment","display_name":"Phoneme-Level Contrastive Learning for User-Defined Keyword Spotting with Flexible Enrollment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355055","doi":"https://doi.org/10.1109/icassp49660.2025.10888312"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5057923762","display_name":"Kewei Li","orcid":"https://orcid.org/0009-0000-4445-4301"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kewei Li","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103235094","display_name":"Hengshun Zhou","orcid":"https://orcid.org/0000-0001-7878-6531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengshun Zhou","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432509","display_name":"Kai Shen","orcid":"https://orcid.org/0000-0003-3432-6802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Shen","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102970284","display_name":"Yusheng Dai","orcid":"https://orcid.org/0000-0002-1290-2568"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusheng Dai","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412670","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2410-2429"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057923762"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89851558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T12031","display_name":"Speech and dialogue systems","score":0.9884999990463257,"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/T12031","display_name":"Speech and dialogue systems","score":0.9884999990463257,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.953000009059906,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9366999864578247,"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":0.9011819362640381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8139805793762207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4883563220500946},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.43363291025161743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38860467076301575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37399527430534363}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9011819362640381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139805793762207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4883563220500946},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.43363291025161743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38860467076301575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37399527430534363}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W2034940213","https://openalex.org/W2122797512","https://openalex.org/W2747874407","https://openalex.org/W2765122878","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2962980711","https://openalex.org/W2963351448","https://openalex.org/W2964187693","https://openalex.org/W2972592723","https://openalex.org/W3035524453","https://openalex.org/W3119913666","https://openalex.org/W3160257947","https://openalex.org/W3162273446","https://openalex.org/W3201143670","https://openalex.org/W4206567542","https://openalex.org/W4283767777","https://openalex.org/W4297841644","https://openalex.org/W4313165328","https://openalex.org/W4372260220","https://openalex.org/W4372266552","https://openalex.org/W4372346399","https://openalex.org/W4380479730","https://openalex.org/W4385208579","https://openalex.org/W4385822437","https://openalex.org/W4385823483","https://openalex.org/W4392902956","https://openalex.org/W4392904395","https://openalex.org/W4392904822","https://openalex.org/W4392932011","https://openalex.org/W4401991201","https://openalex.org/W4402112307","https://openalex.org/W4402112589","https://openalex.org/W6636915900","https://openalex.org/W6845076884","https://openalex.org/W6847363464"],"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":{"User-defined":[0],"keyword":[1],"spotting":[2],"(KWS)":[3],"enhances":[4,75],"the":[5,47,70,76,155,158],"user":[6],"experience":[7],"by":[8],"allowing":[9],"individuals":[10],"to":[11,34,94,103,115,131],"customize":[12],"keywords.":[13],"However,":[14],"in":[15,41],"open-vocabulary":[16],"scenarios,":[17],"most":[18],"existing":[19],"methods":[20,148],"commonly":[21],"suffer":[22],"from":[23],"high":[24],"false":[25],"alarm":[26],"rates":[27],"with":[28],"confusable":[29,51,117],"words":[30],"and":[31,62,65,83,90,99,140],"are":[32],"limited":[33],"either":[35],"audio-only":[36],"or":[37],"text-only":[38],"enrollment.":[39],"Therefore,":[40],"this":[42],"paper,":[43],"we":[44,54,108,136],"first":[45],"explore":[46],"model\u2019s":[48,77],"robustness":[49],"against":[50],"words.":[52],"Specifically,":[53],"propose":[55],"Phoneme-Level":[56],"Contrastive":[57],"Learning":[58],"(PLCL),":[59],"which":[60],"refines":[61],"aligns":[63],"query":[64],"source":[66],"feature":[67],"representations":[68],"at":[69],"phoneme":[71,112],"level.":[72],"This":[73],"method":[74],"disambiguation":[78],"capability":[79],"through":[80],"fine-grained":[81],"positive":[82],"negative":[84],"comparisons":[85],"for":[86,119],"more":[87],"accurate":[88],"alignment,":[89],"it":[91],"is":[92,128],"generalizable":[93],"jointly":[95],"optimize":[96],"both":[97],"audio-text":[98],"audio-audio":[100],"matching,":[101],"adapting":[102],"various":[104],"enrollment":[105,147],"modes.":[106],"Furthermore,":[107],"maintain":[109],"a":[110,125,138,150],"context-agnostic":[111],"memory":[113],"bank":[114],"construct":[116],"negatives":[118],"data":[120],"augmentation.":[121],"Based":[122],"on":[123,154],"this,":[124],"third-category":[126],"discriminator":[127],"specifically":[129],"designed":[130],"distinguish":[132],"hard":[133],"negatives.":[134],"Overall,":[135],"develop":[137],"robust":[139],"flexible":[141],"KWS":[142],"system,":[143],"supporting":[144],"different":[145],"modality":[146],"within":[149],"unified":[151],"framework.":[152],"Verified":[153],"LibriPhrase":[156],"dataset,":[157],"proposed":[159],"approach":[160],"achieves":[161],"state-of-the-art":[162],"performance.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}