{"id":"https://openalex.org/W2936167188","doi":"https://doi.org/10.1109/icassp.2019.8682617","title":"Voice Trigger Detection from Lvcsr Hypothesis Lattices Using Bidirectional Lattice Recurrent Neural Networks","display_name":"Voice Trigger Detection from Lvcsr Hypothesis Lattices Using Bidirectional Lattice Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936167188","doi":"https://doi.org/10.1109/icassp.2019.8682617","mag":"2936167188"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682617","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.00304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055671046","display_name":"Woojay Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Woojay Jeon","raw_affiliation_strings":["Apple One Apple Park Way, Cupertino, California"],"affiliations":[{"raw_affiliation_string":"Apple One Apple Park Way, Cupertino, California","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064950120","display_name":"Chengxi Liu","orcid":"https://orcid.org/0000-0003-0262-5314"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leo Liu","raw_affiliation_strings":["Apple One Apple Park Way, Cupertino, California"],"affiliations":[{"raw_affiliation_string":"Apple One Apple Park Way, Cupertino, California","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033446148","display_name":"H. Benjamin Mason","orcid":"https://orcid.org/0000-0003-4279-2854"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Mason","raw_affiliation_strings":["Apple One Apple Park Way, Cupertino, California"],"affiliations":[{"raw_affiliation_string":"Apple One Apple Park Way, Cupertino, California","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055671046"],"corresponding_institution_ids":["https://openalex.org/I4210153776"],"apc_list":null,"apc_paid":null,"fwci":1.5913,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87540543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6356","last_page":"6360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.8128047585487366},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7058446407318115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6647419929504395},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6021267175674438},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5364649295806885},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5273783206939697},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.523402988910675},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5016093254089355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44904789328575134},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41462060809135437},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36606553196907043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34512338042259216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32564306259155273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128047585487366},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7058446407318115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6647419929504395},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6021267175674438},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5364649295806885},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5273783206939697},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.523402988910675},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5016093254089355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44904789328575134},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41462060809135437},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36606553196907043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34512338042259216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32564306259155273},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682617","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:2003.00304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.00304","pdf_url":"https://arxiv.org/pdf/2003.00304","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:2003.00304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.00304","pdf_url":"https://arxiv.org/pdf/2003.00304","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":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W49437105","https://openalex.org/W2052274902","https://openalex.org/W2103371184","https://openalex.org/W2131774270","https://openalex.org/W2134659216","https://openalex.org/W2405666970","https://openalex.org/W2511962886","https://openalex.org/W2747934816","https://openalex.org/W2889511491","https://openalex.org/W6602023532"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312"],"abstract_inverted_index":{"We":[0,31,74],"propose":[1,75],"a":[2,10,20,28,60,68,77],"method":[3],"to":[4,55],"reduce":[5],"false":[6],"voice":[7],"triggers":[8],"of":[9,19,37,41],"speech-enabled":[11],"personal":[12],"assistant":[13],"by":[14],"post-processing":[15],"the":[16,38,42,49,65,85,98,102],"hypothesis":[17,50],"lattice":[18,51,66],"server-side":[21],"large-vocabulary":[22],"continuous":[23],"speech":[24],"recognizer":[25],"(LVCSR)":[26],"via":[27],"neural":[29],"network.":[30],"first":[32],"discuss":[33],"how":[34],"an":[35],"estimate":[36],"posterior":[39],"probability":[40],"trigger":[43],"phrase":[44],"can":[45,91],"be":[46],"obtained":[47],"from":[48],"using":[52,76,97],"known":[53],"techniques":[54],"perform":[56],"detection,":[57],"then":[58],"investigate":[59],"statistical":[61],"model":[62],"that":[63,89],"processes":[64],"in":[67],"more":[69],"explicitly":[70],"data-driven,":[71],"discriminative":[72],"manner.":[73],"Bidirectional":[78],"Lattice":[79],"Recurrent":[80],"Neural":[81],"Network":[82],"(LatticeRNN)":[83],"for":[84],"task,":[86],"and":[87],"show":[88],"it":[90],"significantly":[92],"improve":[93],"detection":[94],"accuracy":[95],"over":[96],"1-best":[99],"result":[100],"or":[101],"posterior.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-04-25T00:00:00"}