{"id":"https://openalex.org/W4372262245","doi":"https://doi.org/10.1109/icassp49357.2023.10097249","title":"Building Keyword Search System from End-To-End Asr Systems","display_name":"Building Keyword Search System from End-To-End Asr Systems","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262245","doi":"https://doi.org/10.1109/icassp49357.2023.10097249"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097249","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097249","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/A5108823342","display_name":"Ruizhe Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhe Huang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,USA","Human Language Technology Center of Excellence, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garcia-Perera","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA","Human Language Technology Center of Excellence, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089659636","display_name":"Dan Povey","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Povey","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA","Human Language Technology Center of Excellence, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA","Human Language Technology Center of Excellence, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8242563009262085},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.751065194606781},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6110812425613403},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5915209054946899},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5435447692871094},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5277132391929626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49244746565818787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4656223952770233},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4339165687561035},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42587196826934814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36508768796920776},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1868201494216919},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.16310954093933105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09319275617599487},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08244389295578003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242563009262085},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.751065194606781},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6110812425613403},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5915209054946899},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5435447692871094},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5277132391929626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49244746565818787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4656223952770233},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4339165687561035},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42587196826934814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36508768796920776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1868201494216919},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.16310954093933105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09319275617599487},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08244389295578003},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097249","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097249","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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1571931074","https://openalex.org/W2098044214","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2166810516","https://openalex.org/W2167338739","https://openalex.org/W2406918729","https://openalex.org/W2493916176","https://openalex.org/W2526425061","https://openalex.org/W2612800309","https://openalex.org/W2697044473","https://openalex.org/W2746778230","https://openalex.org/W2747874407","https://openalex.org/W2962780374","https://openalex.org/W2963211739","https://openalex.org/W2963311389","https://openalex.org/W3015870704","https://openalex.org/W3096014412","https://openalex.org/W3096524176","https://openalex.org/W3150122400","https://openalex.org/W3181776258","https://openalex.org/W3196482042","https://openalex.org/W3197175124","https://openalex.org/W3202184514","https://openalex.org/W3207815550","https://openalex.org/W3211278025","https://openalex.org/W4210424357","https://openalex.org/W4210811812","https://openalex.org/W4221040649","https://openalex.org/W6631362777","https://openalex.org/W6713982614","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W2560284304","https://openalex.org/W2020540721","https://openalex.org/W2121178211","https://openalex.org/W142374489","https://openalex.org/W2046902062","https://openalex.org/W2624106077","https://openalex.org/W2359001871","https://openalex.org/W4385571594","https://openalex.org/W3157511029","https://openalex.org/W2982718591"],"abstract_inverted_index":{"Keyword":[0],"search":[1],"(KWS)":[2],"systems":[3,37],"are":[4,21,40],"commonly":[5,93],"built":[6],"on":[7,88,132],"top":[8],"of":[9,126],"existing":[10],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"systems.":[15],"However,":[16],"end-to-end":[17],"(E2E)":[18],"ASR":[19,36,57,120,148],"models":[20],"not":[22],"naturally":[23],"equipped":[24],"with":[25],"word-level":[26,127],"timing":[27,65],"information":[28,66],"or":[29,43,71],"confidence.":[30],"Existing":[31],"methods":[32],"for":[33,38,84,144],"re-purposing":[34],"E2E":[35],"KWS":[39,52,133,136],"largely":[41],"heuristic":[42],"model-specific.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,114],"describe":[49],"a":[50,105],"general":[51],"pipeline,":[53],"applicable":[54],"to":[55,118],"any":[56],"model":[58,111],"that":[59,79],"generates":[60],"N-best":[61,89],"lists.":[62],"We":[63,77],"extract":[64],"using":[67,98],"either":[68],"external":[69],"word-aligners,":[70],"time-preserving":[72],"weighted":[73],"finite-state":[74],"transducer-based":[75],"decoders.":[76],"show":[78],"our":[80,116],"light-weight,":[81],"ASR-agnostic":[82],"approach":[83],"confidence":[85,109],"estimation":[86,110],"based":[87],"lists":[90],"outperforms":[91],"other":[92],"used":[94],"heuristics,":[95],"such":[96],"as":[97,150],"the":[99,124,146],"decoder\u2019s":[100],"softmax":[101],"probability,":[102],"and":[103,130],"even":[104],"more":[106],"complicated":[107],"dedicated":[108],"(CEM).":[112],"Finally,":[113],"compare":[115],"performance":[117],"hybrid":[119],"models,":[121],"extensively":[122],"evaluating":[123,145],"impact":[125],"timing,":[128],"confidence,":[129],"recall":[131],"performance.":[134],"Our":[135],"pipeline":[137],"is":[138],"available":[139],"online<sup":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[142],"suitable":[143],"aforementioned":[147],"components":[149],"downstream":[151],"tasks.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}