{"id":"https://openalex.org/W3160255845","doi":"https://doi.org/10.1109/icassp39728.2021.9414330","title":"Improving Identification of System-Directed Speech Utterances by Deep Learning of ASR-Based Word Embeddings and Confidence Metrics","display_name":"Improving Identification of System-Directed Speech Utterances by Deep Learning of ASR-Based Word Embeddings and Confidence Metrics","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160255845","doi":"https://doi.org/10.1109/icassp39728.2021.9414330","mag":"3160255845"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5055077769","display_name":"Vilayphone Vilaysouk","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Vilayphone Vilaysouk","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065094891","display_name":"Amr H. Nour-Eldin","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":"Amr Nour-Eldin","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/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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055077769"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05734283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6379","last_page":"6382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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":0.8613147139549255},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7512906789779663},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.668350100517273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6335442066192627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5372915267944336},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4918375015258789},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.47233834862709045},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.45769956707954407},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4478771984577179},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4468006491661072},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43294867873191833},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4126792550086975},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.11101588606834412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613147139549255},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7512906789779663},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.668350100517273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6335442066192627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5372915267944336},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4918375015258789},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.47233834862709045},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.45769956707954407},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4478771984577179},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4468006491661072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43294867873191833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4126792550086975},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11101588606834412},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W8942335","https://openalex.org/W201747637","https://openalex.org/W1614298861","https://openalex.org/W2295504855","https://openalex.org/W2887080793","https://openalex.org/W2896457183","https://openalex.org/W2950577311","https://openalex.org/W2963050656","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2972549707","https://openalex.org/W3011404287","https://openalex.org/W4246760588","https://openalex.org/W4385245566","https://openalex.org/W6600347796","https://openalex.org/W6608148995","https://openalex.org/W6636510571","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6774998584","https://openalex.org/W6828201991"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"extend":[4],"our":[5],"previous":[6,53],"work":[7],"on":[8],"the":[9,35,38,47,52,58,75,80,98,104,119],"detection":[10],"of":[11,17,51,79,113,118],"system-directed":[12],"speech":[13],"utterances.":[14],"This":[15,82],"type":[16],"binary":[18],"classification":[19,77],"can":[20],"be":[21],"used":[22],"by":[23,63,87],"virtual":[24],"assistants":[25],"to":[26,74,116],"create":[27],"a":[28,108],"more":[29],"natural":[30],"and":[31,37],"fluid":[32],"interaction":[33],"between":[34],"system":[36],"user.":[39],"We":[40],"explore":[41],"two":[42],"methods":[43],"that":[44,117],"both":[45],"improve":[46],"Equal-Error-Rate":[48],"(EER)":[49],"performance":[50,86,111],"model.":[54,81],"The":[55,89],"first":[56,105],"exploits":[57],"supplementary":[59],"information":[60],"independently":[61],"captured":[62],"ASR":[64,68],"models":[65],"through":[66],"integrating":[67],"decoder-based":[69],"features":[70],"as":[71],"additional":[72],"inputs":[73],"final":[76],"stage":[78],"relatively":[83],"improves":[84],"EER":[85,110],"13%.":[88],"second":[90],"proposed":[91],"method":[92],"further":[93],"integrates":[94],"word":[95],"embeddings":[96],"into":[97],"architecture":[99],"and,":[100],"when":[101],"combined":[102],"with":[103],"method,":[106],"achieves":[107],"significant":[109],"improvement":[112],"48%,":[114],"relative":[115],"baseline.":[120]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}