{"id":"https://openalex.org/W2912129510","doi":"https://doi.org/10.1109/icassp.2019.8683565","title":"Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed","display_name":"Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2912129510","doi":"https://doi.org/10.1109/icassp.2019.8683565","mag":"2912129510"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.00570","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030074803","display_name":"Atta Norouzian","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Atta Norouzian","raw_affiliation_strings":["Nuance Communications"],"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114106696","display_name":"Bogdan Mazoure","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bogdan Mazoure","raw_affiliation_strings":["McGill University, Canada","(McGill University, Canada)"],"affiliations":[{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"(McGill University, Canada)","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011793520","display_name":"Dermot Connolly","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dermot Connolly","raw_affiliation_strings":["Nuance Communications"],"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017400582","display_name":"Daniel Willett","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Daniel Willett","raw_affiliation_strings":["Nuance Communications"],"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030074803"],"corresponding_institution_ids":["https://openalex.org/I1292318990"],"apc_list":null,"apc_paid":null,"fwci":0.1445,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5477514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7310","last_page":"7314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.7931145429611206},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7782418727874756},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6691163778305054},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6495223641395569},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6168832778930664},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.548164963722229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4354182779788971},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4308120608329773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3802722692489624},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24651458859443665},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07748726010322571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931145429611206},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7782418727874756},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6691163778305054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6495223641395569},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6168832778930664},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.548164963722229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4354182779788971},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4308120608329773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3802722692489624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24651458859443665},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07748726010322571},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.00570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.00570","pdf_url":"https://arxiv.org/pdf/1902.00570","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"},{"id":"mag:2912129510","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1902.00570v1","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1902.00570","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.00570","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.00570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.00570","pdf_url":"https://arxiv.org/pdf/1902.00570","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":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2912129510.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W8942335","https://openalex.org/W201747637","https://openalex.org/W601101228","https://openalex.org/W2035284256","https://openalex.org/W2082927806","https://openalex.org/W2090777335","https://openalex.org/W2144005487","https://openalex.org/W2295504855","https://openalex.org/W2396814492","https://openalex.org/W2404045576","https://openalex.org/W2405622356","https://openalex.org/W2791874451","https://openalex.org/W2887080793","https://openalex.org/W2962736520","https://openalex.org/W2962922562","https://openalex.org/W2963403868","https://openalex.org/W2964308564","https://openalex.org/W6600347796","https://openalex.org/W6608148995","https://openalex.org/W6618255145","https://openalex.org/W6679434410","https://openalex.org/W6681409903","https://openalex.org/W6712317599","https://openalex.org/W6713452507","https://openalex.org/W6713590768","https://openalex.org/W6739901393","https://openalex.org/W6828201991"],"related_works":["https://openalex.org/W2963050656","https://openalex.org/W2909274332","https://openalex.org/W3012945836","https://openalex.org/W2964272940","https://openalex.org/W1588565267","https://openalex.org/W2613634895","https://openalex.org/W2490668544","https://openalex.org/W2604132379","https://openalex.org/W3092318106","https://openalex.org/W2612030847","https://openalex.org/W2403440562","https://openalex.org/W3131384824","https://openalex.org/W3005701363","https://openalex.org/W1551722583","https://openalex.org/W3174525209","https://openalex.org/W138549276","https://openalex.org/W2397313144","https://openalex.org/W2133764590","https://openalex.org/W2100613388","https://openalex.org/W2407151108"],"abstract_inverted_index":{"Voice":[0],"controlled":[1],"virtual":[2],"assistants":[3],"(VAs)":[4],"are":[5],"now":[6],"available":[7],"in":[8,14],"smartphones,":[9],"cars,":[10],"and":[11,87,124,164,191],"standalone":[12],"devices":[13],"homes.":[15],"In":[16,77,91,140],"most":[17],"cases,":[18],"the":[19,25,36,42,46,54,60,64,69,80,111,144,152,157,162,177,183],"user":[20,55,70],"needs":[21],"to":[22,38,62,73,83,154,165],"first":[23],"\"wake-up\"":[24],"VA":[26,37,61],"by":[27],"saying":[28,45],"a":[29,96,118],"particular":[30],"word/phrase":[31],"every":[32,50],"time":[33],"he/she":[34],"wants":[35],"do":[39],"something.":[40],"Eliminating":[41],"need":[43],"for":[44,49,102,137,150],"wake-up":[47],"word":[48],"interaction":[51],"could":[52],"improve":[53,166],"experience.":[56],"This":[57],"would":[58],"require":[59],"have":[63],"capability":[65],"of":[66,98,121,134,146,161,168,189],"understanding":[67],"whether":[68],"is":[71,82,115],"talking":[72],"it":[74],"or":[75],"not.":[76],"other":[78],"words,":[79],"challenge":[81],"distinguish":[84],"between":[85],"system-directed":[86],"non-system-directed":[88],"speech":[89],"utterances.":[90],"this":[92,104,138],"paper,":[93],"we":[94,142],"present":[95],"number":[97],"neural":[99],"network":[100],"architectures":[101],"tackling":[103],"classification":[105],"problem":[106],"based":[107],"on":[108,156,193],"using":[109],"only":[110],"acoustic":[112],"signal.":[113],"It":[114],"shown":[116],"that":[117,176],"model":[119,153,184],"comprised":[120],"convolutional,":[122],"recurrent,":[123],"feed-forward":[125],"layers":[126],"can":[127],"achieve":[128],"an":[129,147,187],"equal":[130],"error":[131],"rate":[132],"(EER)":[133],"below":[135],"20%":[136],"task.":[139],"addition,":[141],"investigate":[143],"use":[145],"attention":[148,179],"mechanism":[149,180],"helping":[151],"focus":[155],"more":[158],"important":[159],"parts":[160],"signal":[163],"handling":[167],"variable":[169],"length":[170],"inputs":[171],"sequences.":[172],"The":[173],"results":[174],"show":[175],"proposed":[178],"significantly":[181],"improves":[182],"accuracy":[185],"achieving":[186],"EER":[188],"16.25%":[190],"15.62%":[192],"two":[194],"distinct":[195],"realistic":[196],"datasets.":[197]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}