{"id":"https://openalex.org/W2962707338","doi":"https://doi.org/10.1109/asru.2017.8268974","title":"Streaming small-footprint keyword spotting using sequence-to-sequence models","display_name":"Streaming small-footprint keyword spotting using sequence-to-sequence models","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2962707338","doi":"https://doi.org/10.1109/asru.2017.8268974","mag":"2962707338"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268974","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Google Inc., Mountain View, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":["Google Inc., Mountain View, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111514705","display_name":"Kanishka Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanishka Rao","raw_affiliation_strings":["Google Inc., Mountain View, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318020","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7824-4839"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Google Inc., Mountain View, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024680544","display_name":"Anton Bakhtin","orcid":"https://orcid.org/0000-0002-3320-2341"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anton Bakhtin","raw_affiliation_strings":["Google Inc., Mountain View, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048236120","display_name":"Ian McGraw","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian McGraw","raw_affiliation_strings":["Google Inc., Mountain View, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101319167"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":8.3857,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":{"value":0.98060114,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"474","last_page":"481"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9585707783699036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8431726098060608},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7077664136886597},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6953519582748413},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6828185319900513},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6615159511566162},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5903491377830505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5787897706031799},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5442824363708496},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4891810715198517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4675140976905823},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43559014797210693},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4303203523159027}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9585707783699036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431726098060608},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7077664136886597},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6953519582748413},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6828185319900513},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6615159511566162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5903491377830505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787897706031799},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5442824363708496},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4891810715198517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4675140976905823},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43559014797210693},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4303203523159027},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268974","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W23025778","https://openalex.org/W114193738","https://openalex.org/W1485222997","https://openalex.org/W1489125746","https://openalex.org/W1494604982","https://openalex.org/W1496120315","https://openalex.org/W1525371959","https://openalex.org/W1553469512","https://openalex.org/W1689711448","https://openalex.org/W1828163288","https://openalex.org/W2034940213","https://openalex.org/W2040226630","https://openalex.org/W2064675550","https://openalex.org/W2067392428","https://openalex.org/W2095126095","https://openalex.org/W2122797512","https://openalex.org/W2127141656","https://openalex.org/W2128833328","https://openalex.org/W2143612262","https://openalex.org/W2151244813","https://openalex.org/W2168231600","https://openalex.org/W2171019095","https://openalex.org/W2212465773","https://openalex.org/W2271840356","https://openalex.org/W2293829681","https://openalex.org/W2312434537","https://openalex.org/W2327501763","https://openalex.org/W2397840928","https://openalex.org/W2407023693","https://openalex.org/W2442329935","https://openalex.org/W2497335382","https://openalex.org/W2507580616","https://openalex.org/W2510945575","https://openalex.org/W2545177271","https://openalex.org/W2558258029","https://openalex.org/W2587529061","https://openalex.org/W2602634800","https://openalex.org/W2608712415","https://openalex.org/W2612800309","https://openalex.org/W2622203030","https://openalex.org/W2697044473","https://openalex.org/W2746192915","https://openalex.org/W2749514303","https://openalex.org/W2750499125","https://openalex.org/W2953219395","https://openalex.org/W2962765220","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963311389","https://openalex.org/W2963920996","https://openalex.org/W3098773154","https://openalex.org/W4294621971","https://openalex.org/W6600906190","https://openalex.org/W6604666349","https://openalex.org/W6629052376","https://openalex.org/W6637409405","https://openalex.org/W6638749077","https://openalex.org/W6678774376","https://openalex.org/W6684859321","https://openalex.org/W6688089860","https://openalex.org/W6714171909","https://openalex.org/W6718561954","https://openalex.org/W6728910023","https://openalex.org/W6729959887","https://openalex.org/W6743440867"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638"],"abstract_inverted_index":{"We":[0],"develop":[1],"streaming":[2],"keyword":[3,47,63,78],"spotting":[4],"systems":[5,82],"using":[6],"a":[7,67,76,86,100],"recurrent":[8],"neural":[9],"network":[10],"transducer":[11],"(RNN-T)":[12],"model:":[13],"an":[14],"all-neural,":[15],"end-to-end":[16],"trained,":[17],"sequence-to-sequence":[18],"model":[19,26],"which":[20,70,96],"jointly":[21],"learns":[22],"acoustic":[23],"and":[24],"language":[25,103],"components.":[27],"Our":[28,81],"models":[29,58],"are":[30,83],"trained":[31],"to":[32,44,55,59],"predict":[33],"either":[34],"phonemes":[35],"or":[36],"graphemes":[37],"as":[38],"subword":[39],"units,":[40],"thus":[41],"allowing":[42],"us":[43],"detect":[45],"arbitrary":[46],"phrases,":[48],"without":[49],"any":[50],"out-of-vocabulary":[51],"words.":[52],"In":[53],"order":[54],"adapt":[56],"the":[57,60,72,110,118],"requirements":[61],"of":[62,79],"spotting,":[64],"we":[65],"propose":[66],"novel":[68],"technique":[69,113],"biases":[71],"RNN-T":[73,107],"system":[74,108],"towards":[75],"specific":[77],"interest.":[80],"compared":[84],"against":[85],"strong":[87],"sequence-trained,":[88],"connectionist":[89],"temporal":[90],"classification":[91],"(CTC)":[92],"based":[93],"\u201ckeyword-filler\u201d":[94],"baseline,":[95],"is":[97],"augmented":[98],"with":[99,109],"separate":[101],"phoneme":[102],"model.":[104],"Overall,":[105],"our":[106],"proposed":[111],"biasing":[112],"significantly":[114],"improves":[115],"performance":[116],"over":[117],"baseline":[119],"system.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
