{"id":"https://openalex.org/W4391021514","doi":"https://doi.org/10.1109/asru57964.2023.10389755","title":"U2-KWS: Unified Two-Pass Open-Vocabulary Keyword Spotting with Keyword Bias","display_name":"U2-KWS: Unified Two-Pass Open-Vocabulary Keyword Spotting with Keyword Bias","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021514","doi":"https://doi.org/10.1109/asru57964.2023.10389755"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100437589","display_name":"Ao Zhang","orcid":"https://orcid.org/0000-0002-1536-2413"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Space AI, Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Space AI, Li Auto","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113119330","display_name":"Kaixun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixun Huang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101359034","display_name":"Yong Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Zou","raw_affiliation_strings":["Space AI, Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Space AI, Li Auto","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343852","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0001-6239-1180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Space AI, Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Space AI, Li Auto","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5245,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86082731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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":0.9891277551651001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8669919967651367},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7204902172088623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5989489555358887},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5601015686988831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5464918613433838},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47803816199302673},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.41019734740257263}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9891277551651001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8669919967651367},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7204902172088623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5989489555358887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5601015686988831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5464918613433838},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47803816199302673},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.41019734740257263},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W2034940213","https://openalex.org/W2212465773","https://openalex.org/W2407023693","https://openalex.org/W2510945575","https://openalex.org/W2652238127","https://openalex.org/W2797759721","https://openalex.org/W2886319145","https://openalex.org/W2936774411","https://openalex.org/W2962707338","https://openalex.org/W2963242190","https://openalex.org/W3001493895","https://openalex.org/W3095694146","https://openalex.org/W3096662840","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3111562797","https://openalex.org/W3161038873","https://openalex.org/W3161425572","https://openalex.org/W3162273446","https://openalex.org/W3163203022","https://openalex.org/W3163582231","https://openalex.org/W3196509839","https://openalex.org/W3197478142","https://openalex.org/W3198035615","https://openalex.org/W3207815550","https://openalex.org/W4224932156","https://openalex.org/W4283767777","https://openalex.org/W4283828241","https://openalex.org/W4287864706","https://openalex.org/W4372339449","https://openalex.org/W4372349408","https://openalex.org/W6688089860","https://openalex.org/W6729959887","https://openalex.org/W6739901393","https://openalex.org/W6774097463","https://openalex.org/W6787040858"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Open-vocabulary":[0],"keyword":[1,80,111],"spotting":[2],"(KWS),":[3],"which":[4],"allows":[5],"users":[6],"to":[7,32,77,91,96,147,160],"customize":[8],"keywords,":[9,100],"has":[10],"attracted":[11],"increasingly":[12],"more":[13],"interest.":[14],"However,":[15],"existing":[16],"methods":[17],"based":[18],"on":[19,124],"acoustic":[20,26,38],"models":[21],"and":[22,82,109,115,128],"post-processing":[23],"train":[24],"the":[25,37,42,61,69,73,83,87,103,148,154],"model":[27,33,39,64,76,90],"with":[28],"ASR":[29,63],"training":[30,105],"criteria":[31],"all":[34],"phonemes,":[35],"making":[36],"under-optimized":[40],"for":[41,107],"KWS":[43,56,151],"task.":[44],"To":[45],"solve":[46],"this":[47],"problem,":[48],"we":[49,67,101],"propose":[50],"a":[51,137],"novel":[52],"unified":[53],"two-pass":[54,62],"open-vocabulary":[55],"(U2-KWS)":[57],"framework":[58],"inspired":[59],"by":[60,113],"U2.":[65],"Specifically,":[66],"employ":[68],"CTC":[70],"branch":[71,85],"as":[72,86],"first":[74],"stage":[75,89],"detect":[78],"potential":[79],"candidates":[81],"decoder":[84],"second":[88],"validate":[92],"candidates.":[93],"In":[94],"order":[95],"enhance":[97],"any":[98],"customized":[99,150],"redesign":[102],"U2":[104],"procedure":[106],"U2-KWS":[108,134],"add":[110],"information":[112],"audio":[114],"text":[116],"cross-attention":[117],"into":[118],"both":[119],"branches.":[120],"We":[121],"perform":[122],"experiments":[123],"our":[125],"internal":[126],"dataset":[127],"Aishell-1.":[129],"The":[130],"results":[131],"show":[132],"that":[133],"can":[135],"achieve":[136],"significant":[138],"relative":[139],"wake-up":[140],"rate":[141,157],"improvement":[142],"of":[143],"41":[144],"%":[145],"compared":[146],"traditional":[149],"systems":[152],"when":[153],"false":[155],"alarm":[156],"is":[158],"fixed":[159],"0.5":[161],"times":[162],"per":[163],"hour.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
