{"id":"https://openalex.org/W2578392894","doi":"https://doi.org/10.1109/jstsp.2017.2759726","title":"End-to-End ASR-Free Keyword Search From Speech","display_name":"End-to-End ASR-Free Keyword Search From Speech","publication_year":2017,"publication_date":"2017-10-05","ids":{"openalex":"https://openalex.org/W2578392894","doi":"https://doi.org/10.1109/jstsp.2017.2759726","mag":"2578392894"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2017.2759726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2759726","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1701.04313","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0002-2340-1144","affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0003-1780-4390","affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0002-8049-2345","affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0002-1343-6837","affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":9.3709,"has_fulltext":true,"cited_by_count":91,"citation_normalized_percentile":{"value":0.98285408,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"11","issue":"8","first_page":"1351","last_page":"1359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T10860","display_name":"Speech 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8453149795532227},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7992821931838989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7059212327003479},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6844504475593567},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6499436497688293},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48428648710250854},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4824000597000122},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46247899532318115},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4545820951461792},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45428940653800964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44228994846343994},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4161829352378845},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4100494384765625},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2660282850265503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453149795532227},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7992821931838989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7059212327003479},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6844504475593567},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6499436497688293},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48428648710250854},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4824000597000122},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46247899532318115},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4545820951461792},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45428940653800964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44228994846343994},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4161829352378845},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4100494384765625},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2660282850265503},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2017.2759726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2759726","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1701.04313","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.04313","pdf_url":"https://arxiv.org/pdf/1701.04313","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1701.04313","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.04313","pdf_url":"https://arxiv.org/pdf/1701.04313","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308668","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2578392894.pdf","grobid_xml":"https://content.openalex.org/works/W2578392894.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W196761320","https://openalex.org/W1489125746","https://openalex.org/W1496120315","https://openalex.org/W1522301498","https://openalex.org/W1553004968","https://openalex.org/W1736701665","https://openalex.org/W1924770834","https://openalex.org/W1938755728","https://openalex.org/W2059652594","https://openalex.org/W2113457868","https://openalex.org/W2117141689","https://openalex.org/W2126203737","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2160815625","https://openalex.org/W2167338739","https://openalex.org/W2171019095","https://openalex.org/W2185726469","https://openalex.org/W2190506272","https://openalex.org/W2291975472","https://openalex.org/W2384495648","https://openalex.org/W2403195671","https://openalex.org/W2508907749","https://openalex.org/W2519224033","https://openalex.org/W2545177271","https://openalex.org/W2566587499","https://openalex.org/W2597757402","https://openalex.org/W2951216052","https://openalex.org/W2951559648","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963217176","https://openalex.org/W2963311389","https://openalex.org/W2963571336","https://openalex.org/W2963920996","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W6608133726","https://openalex.org/W6629052376","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6640598943","https://openalex.org/W6676725880","https://openalex.org/W6677452488","https://openalex.org/W6679434410","https://openalex.org/W6686651311","https://openalex.org/W6713280142","https://openalex.org/W6731763572","https://openalex.org/W6735390525"],"related_works":["https://openalex.org/W3161425572","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2069071271","https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2960533729","https://openalex.org/W2916997151"],"abstract_inverted_index":{"Conventional":[0],"keyword":[1],"search":[2],"(KWS)":[3],"systems":[4,35],"for":[5],"speech":[6,23,58,107],"databases":[7],"match":[8],"the":[9,14,30,39,106,121,140,144,175,187,194,211,214],"input":[10,122,131],"text":[11,123],"query":[12,114,128,141],"to":[13,37,132,174,185,209],"set":[15],"of":[16,42,86,105,120,196,213],"word":[17],"hypotheses":[18],"generated":[19],"by":[20,168,217],"an":[21,48,64,77,118],"automatic":[22],"recognition":[24],"(ASR)":[25],"system":[26,50,67,84],"from":[27],"utterances":[28],"in":[29,143,155,203],"database.":[31],"Hence,":[32],"such":[33],"KWS":[34,79,83,166,204,221],"attempt":[36,208],"solve":[38],"complex":[40],"problem":[41],"ASR":[43,49],"as":[44],"a":[45,53,93,102,113,133,200,219],"precursor.":[46],"Training":[47],"itself":[51],"is":[52,183],"time-consuming":[54],"process":[55],"requiring":[56],"transcribed":[57],"data.":[59],"Our":[60],"prior":[61,153],"work":[62,154],"presented":[63],"ASR-free":[65,82,165],"end-to-end":[66],"that":[68,100,116,137,181],"needed":[69],"minimal":[70],"supervision":[71],"and":[72,127],"trained":[73],"significantly":[74,160],"faster":[75],"than":[76,193],"ASR-based":[78],"system.":[80],"The":[81,89,109,125],"consisted":[85],"three":[87],"subsystems.":[88],"first":[90],"subsystem":[91,111],"was":[92,112],"recurrent":[94],"neural":[95,135],"network":[96,136],"based":[97],"acoustic":[98,126,145,176,188],"encoder":[99,115,189],"extracted":[101],"finite-dimensional":[103],"embedding":[104,119],"utterance.":[108],"second":[110],"produced":[117],"query.":[124],"embeddings":[129],"were":[130],"feedforward":[134],"predicted":[138],"whether":[139],"occurred":[142],"utterance":[146],"or":[147],"not.":[148],"This":[149],"paper":[150],"extends":[151],"our":[152,163],"several":[156],"ways.":[157],"First,":[158],"we":[159,179,207],"improve":[161],"upon":[162],"previous":[164],"results":[167],"nearly":[169],"20%":[170],"relative":[171],"through":[172],"improvements":[173],"encoder.":[177],"Next,":[178],"show":[180],"it":[182],"possible":[184],"train":[186],"on":[190],"languages":[191],"other":[192],"language":[195],"interest":[197],"with":[198],"only":[199],"small":[201],"drop":[202],"performance.":[205],"Finally,":[206],"predict":[210],"location":[212],"detected":[215],"keywords":[216],"training":[218],"location-sensitive":[220],"network.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}