{"id":"https://openalex.org/W2963311389","doi":"https://doi.org/10.1109/icassp.2017.7953076","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":"2017-03-01","ids":{"openalex":"https://openalex.org/W2963311389","doi":"https://doi.org/10.1109/icassp.2017.7953076","mag":"2963311389"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, New York","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, New York","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4840","last_page":"4844"},"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8406203985214233},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7298794388771057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7090529203414917},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6855342984199524},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6489940285682678},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4924670159816742},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4834202527999878},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45724180340766907},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45666390657424927},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4517379403114319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44670188426971436},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4428445100784302},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41205552220344543},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24608522653579712}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406203985214233},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7298794388771057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7090529203414917},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6855342984199524},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6489940285682678},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4924670159816742},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4834202527999878},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45724180340766907},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45666390657424927},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4517379403114319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44670188426971436},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4428445100784302},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41205552220344543},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24608522653579712},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W196761320","https://openalex.org/W1496120315","https://openalex.org/W1522301498","https://openalex.org/W1924770834","https://openalex.org/W1938755728","https://openalex.org/W2059652594","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/W2190506272","https://openalex.org/W2291975472","https://openalex.org/W2384495648","https://openalex.org/W2403195671","https://openalex.org/W2508907749","https://openalex.org/W2519224033","https://openalex.org/W2951559648","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963217176","https://openalex.org/W2963571336","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W6608133726","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6640598943","https://openalex.org/W6679434410","https://openalex.org/W6697040452","https://openalex.org/W6713280142","https://openalex.org/W6726720044"],"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/W2529301793","https://openalex.org/W2388033618","https://openalex.org/W3161425572","https://openalex.org/W1494604982","https://openalex.org/W2121652828"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"systems":[2,25],"have":[3],"achieved":[4],"competitive":[5],"results":[6],"compared":[7],"to":[8,29,90,129],"conventional":[9,157],"hybrid":[10],"hidden":[11],"Markov":[12],"model":[13,106],"(HMM)-deep":[14],"neural":[15,84,113,133],"network":[16,85,134],"based":[17],"automatic":[18],"speech":[19,65],"recognition":[20],"(ASR)":[21],"systems.":[22],"Such":[23],"E2E":[24,71,148],"are":[26,127],"attractive":[27],"due":[28],"the":[30,51,92,116,138,142],"lack":[31],"of":[32,53,75],"dependence":[33],"on":[34],"alignments":[35],"between":[36],"input":[37,128],"acoustic":[38,87,117,143],"and":[39,118,160],"output":[40],"grapheme":[41],"or":[42,145],"HMM":[43],"state":[44],"sequence":[45],"during":[46],"training.":[47],"This":[48,147],"paper":[49],"explores":[50],"design":[52],"an":[54],"ASR-free":[55,149],"end-to-end":[56],"system":[57,73,151,159],"for":[58],"text":[59,119],"query-based":[60],"keyword":[61],"search":[62],"(KWS)":[63],"from":[64,110],"trained":[66,89],"with":[67],"minimal":[68],"supervision.":[69],"Our":[70],"KWS":[72,150],"consists":[74],"three":[76],"sub-systems.":[77],"The":[78,98],"first":[79],"sub-system":[80,100],"is":[81,101],"a":[82,95,102,111,130,156],"recurrent":[83],"(RNN)-based":[86],"auto-encoder":[88],"reconstruct":[91],"audio":[93],"through":[94],"finite-dimensional":[96],"representation.":[97],"second":[99],"character-level":[103],"RNN":[104],"language":[105],"using":[107],"embeddings":[108,121],"learned":[109],"convolutional":[112],"network.":[114],"Since":[115],"query":[120,139],"occupy":[122],"different":[123],"representation":[124],"spaces,":[125],"they":[126],"third":[131],"feed-forward":[132],"that":[135],"predicts":[136],"whether":[137],"occurs":[140],"in":[141],"utterance":[144],"not.":[146],"performs":[152],"respectably":[153],"despite":[154],"lacking":[155],"ASR":[158],"trains":[161],"much":[162],"faster.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}