{"id":"https://openalex.org/W3158180975","doi":"https://doi.org/10.21437/interspeech.2021-204","title":"Personalized Keyphrase Detection Using Speaker and Environment Information","display_name":"Personalized Keyphrase Detection Using Speaker and Environment Information","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3158180975","doi":"https://doi.org/10.21437/interspeech.2021-204","mag":"3158180975"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-204","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/2104.13970","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003481800","display_name":"Rajeev Rikhye","orcid":"https://orcid.org/0000-0003-2011-2897"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rajeev Rikhye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Liang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037644321","display_name":"Ding Zhao","orcid":"https://orcid.org/0000-0002-9400-8446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069544799","display_name":"Yiteng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143921","display_name":"Arden University","ror":"https://ror.org/059hhvg49","country_code":"GB","type":"education","lineage":["https://openalex.org/I2800893096","https://openalex.org/I4210143921"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yiteng Huang","raw_affiliation_strings":["Arden"],"affiliations":[{"raw_affiliation_string":"Arden","institution_ids":["https://openalex.org/I4210143921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048236120","display_name":"Ian McGraw","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ian McGraw","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5003481800"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62155408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4204","last_page":"4208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9955000281333923,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9951000213623047,"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":0.8402557969093323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.72600919008255},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6525156497955322},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6205099821090698},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5967656970024109},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5250760912895203},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5059635043144226},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4908340573310852},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4882700443267822},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4736976623535156},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4573480784893036},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4360209107398987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4214697480201721},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3213252127170563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402557969093323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.72600919008255},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6525156497955322},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6205099821090698},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5967656970024109},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5250760912895203},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5059635043144226},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4908340573310852},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4882700443267822},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4736976623535156},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4573480784893036},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4360209107398987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4214697480201721},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3213252127170563},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-204","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.13970","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.13970","pdf_url":"https://arxiv.org/pdf/2104.13970","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:3158180975","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.13970","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.2104.13970","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.13970","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:2104.13970","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.13970","pdf_url":"https://arxiv.org/pdf/2104.13970","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158180975.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1635512741","https://openalex.org/W1689711448","https://openalex.org/W1828163288","https://openalex.org/W1971168548","https://openalex.org/W2034940213","https://openalex.org/W2094536997","https://openalex.org/W2110075977","https://openalex.org/W2136439176","https://openalex.org/W2221409856","https://openalex.org/W2527729766","https://openalex.org/W2617258110","https://openalex.org/W2696967604","https://openalex.org/W2734774145","https://openalex.org/W2764043458","https://openalex.org/W2782717521","https://openalex.org/W2787752687","https://openalex.org/W2808631503","https://openalex.org/W2937769560","https://openalex.org/W2953311167","https://openalex.org/W2962707338","https://openalex.org/W2962760690","https://openalex.org/W2962788625","https://openalex.org/W2963414149","https://openalex.org/W2963977978","https://openalex.org/W2964243274","https://openalex.org/W2973054998","https://openalex.org/W2973062255","https://openalex.org/W2975044525","https://openalex.org/W3008181812","https://openalex.org/W3015194534","https://openalex.org/W3015598461","https://openalex.org/W3016234652","https://openalex.org/W3035268204","https://openalex.org/W3044278286","https://openalex.org/W3083872384","https://openalex.org/W3096090308","https://openalex.org/W3143332423","https://openalex.org/W3197845638"],"related_works":["https://openalex.org/W2115619557","https://openalex.org/W2584329820","https://openalex.org/W2106248981","https://openalex.org/W292968312","https://openalex.org/W3211614993","https://openalex.org/W2339276216","https://openalex.org/W3163929126","https://openalex.org/W2993859014","https://openalex.org/W2140653242","https://openalex.org/W1519782245","https://openalex.org/W2902256452","https://openalex.org/W3016048045","https://openalex.org/W3126427729","https://openalex.org/W2142328794","https://openalex.org/W3087422378","https://openalex.org/W2126639624","https://openalex.org/W3198543387","https://openalex.org/W2044812127","https://openalex.org/W2143383629","https://openalex.org/W3158457675"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"a":[5,24,41,58],"streaming":[6],"keyphrase":[7,104],"detection":[8],"system":[9,28],"that":[10,90],"can":[11],"be":[12],"easily":[13],"customized":[14],"to":[15,64,82],"accurately":[16],"detect":[17],"any":[18],"phrase":[19],"composed":[20],"of":[21,50,68,102],"words":[22],"from":[23],"large":[25],"vocabulary.":[26],"The":[27],"is":[29,62,80],"implemented":[30],"with":[31],"an":[32,74],"end-to-end":[33],"trained":[34],"automatic":[35],"speech":[36],"recognition":[37],"(ASR)":[38],"model":[39,61,95,110],"and":[40,73,111],"text-independent":[42,92],"speaker":[43,59,70,93,108],"verification":[44,71,94],"model.":[45],"To":[46],"address":[47],"the":[48,65,69,91,98,103,107],"challenge":[49],"detecting":[51],"these":[52],"keyphrases":[53],"under":[54],"various":[55],"noisy":[56],"conditions,":[57],"separation":[60,109],"added":[63],"feature":[66],"frontend":[67],"model,":[72],"adaptive":[75,112],"noise":[76,85,113],"cancellation":[77,114],"(ANC)":[78],"algorithm":[79],"included":[81],"exploit":[83],"cross-microphone":[84],"coherence.":[86],"Our":[87],"experiments":[88],"show":[89],"largely":[96,115],"reduces":[97],"false":[99,117],"triggering":[100],"rate":[101],"detection,":[105],"while":[106],"reduce":[116],"rejections.":[118]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}