{"id":"https://openalex.org/W4372339449","doi":"https://doi.org/10.1109/icassp49357.2023.10094747","title":"Keyword-Specific Acoustic Model Pruning for Open-Vocabulary Keyword Spotting","display_name":"Keyword-Specific Acoustic Model Pruning for Open-Vocabulary Keyword Spotting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372339449","doi":"https://doi.org/10.1109/icassp49357.2023.10094747"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094747","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/A5101620888","display_name":"Yujie Yang","orcid":"https://orcid.org/0000-0001-7222-0019"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Yang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342380","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0003-2140-2546"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Peng Cheng Lab, Shenzhen, China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Peng Cheng Lab, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.725,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66799438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9958000183105469,"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":0.9357948303222656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8440375328063965},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6483733057975769},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6341292262077332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6239879131317139},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6173274517059326},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48476165533065796},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4816130995750427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4553655982017517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.407580703496933},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1898406445980072},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06657242774963379}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9357948303222656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440375328063965},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6483733057975769},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6341292262077332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6239879131317139},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6173274517059326},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48476165533065796},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4816130995750427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553655982017517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.407580703496933},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1898406445980072},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06657242774963379},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094747","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":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1613249581","https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2547875792","https://openalex.org/W2551895583","https://openalex.org/W2962707338","https://openalex.org/W2963242190","https://openalex.org/W2974893078","https://openalex.org/W2995463996","https://openalex.org/W3005273253","https://openalex.org/W3095694146","https://openalex.org/W3100148727","https://openalex.org/W3105966348","https://openalex.org/W3161980820","https://openalex.org/W3163582231","https://openalex.org/W3196509839","https://openalex.org/W4223511625","https://openalex.org/W4224932156","https://openalex.org/W4226135414","https://openalex.org/W4287121196","https://openalex.org/W4287864706","https://openalex.org/W4295116917","https://openalex.org/W6687483927","https://openalex.org/W6767327937","https://openalex.org/W6773667195","https://openalex.org/W6796487566"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4286904253","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2386245264","https://openalex.org/W4389912005"],"abstract_inverted_index":{"The":[0],"open-vocabulary":[1],"KWS":[2,84],"system":[3],"allows":[4],"users":[5],"to":[6,46,71,108],"customize":[7],"wake":[8],"words,":[9],"but":[10],"its":[11],"application":[12],"is":[13],"limited":[14],"by":[15],"the":[16,57,61,64,82,86,91,102,110,118,127],"model":[17,27],"size.":[18],"In":[19],"this":[20,52],"paper,":[21],"we":[22,54],"design":[23],"a":[24,97],"dynamic":[25],"acoustic":[26,34,99],"with":[28,36,63],"input-dependent":[29],"parameters.":[30],"We":[31],"find":[32],"that":[33,104,117],"frames":[35],"similar":[37,40],"pronunciation":[38],"generate":[39],"subnetworks,":[41],"and":[42,101],"different":[43,48,73],"parameters":[44,103,128],"contribute":[45,107],"recognizing":[47,88,109],"phonemes.":[49],"Based":[50],"on":[51],"observation,":[53],"further":[55],"constrain":[56],"structural":[58],"similarity":[59],"among":[60],"subnetworks":[62,70,87],"same":[65],"phoneme":[66],"pseudo-label,":[67],"thus":[68],"independent":[69],"recognize":[72],"phonemes":[74,89],"could":[75],"be":[76,94],"pruned":[77,113],"out.":[78],"When":[79],"used":[80],"in":[81,90],"end-to-end":[83],"system,":[85],"keyword":[92,111],"would":[93],"combined":[95],"as":[96],"keyword-specific":[98],"model,":[100],"do":[105],"not":[106],"are":[112],"off.":[114],"Experiments":[115],"demonstrate":[116],"proposed":[119],"method":[120],"can":[121],"prune":[122],"more":[123],"than":[124],"80%":[125],"of":[126],"without":[129],"performance":[130],"loss.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}