{"id":"https://openalex.org/W2889933531","doi":"https://doi.org/10.1109/slt.2018.8639614","title":"LSTM-Based Whisper Detection","display_name":"LSTM-Based Whisper Detection","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2889933531","doi":"https://doi.org/10.1109/slt.2018.8639614","mag":"2889933531"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5030676855","display_name":"Zeynab Raeesy","orcid":"https://orcid.org/0000-0002-7153-1963"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeynab Raeesy","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061172909","display_name":"Kellen Gillespie","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kellen Gillespie","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102725787","display_name":"Chengyuan Ma","orcid":"https://orcid.org/0000-0001-5126-5883"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengyuan Ma","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061572171","display_name":"Jiacheng Gu","orcid":"https://orcid.org/0000-0002-8793-1558"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiacheng Gu","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012163532","display_name":"Bj\u00f6rn Hoffmeister","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bjorn Hoffmeister","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3302,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8198527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"84","issue":null,"first_page":"139","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.8818120956420898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6173179745674133},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5997157096862793},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5950679779052734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5596430897712708},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5295482873916626},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.47714969515800476},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.464365690946579},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.450065016746521},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4393406808376312},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.43529802560806274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4349946975708008},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4329540431499481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8818120956420898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6173179745674133},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5997157096862793},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5950679779052734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5596430897712708},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5295482873916626},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.47714969515800476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.464365690946579},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.450065016746521},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4393406808376312},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.43529802560806274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4349946975708008},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4329540431499481},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W15516501","https://openalex.org/W36345725","https://openalex.org/W37326695","https://openalex.org/W41355022","https://openalex.org/W48525746","https://openalex.org/W177407077","https://openalex.org/W1646027691","https://openalex.org/W1837709900","https://openalex.org/W2032362923","https://openalex.org/W2048497537","https://openalex.org/W2057653135","https://openalex.org/W2064675550","https://openalex.org/W2107878631","https://openalex.org/W2131981197","https://openalex.org/W2149053750","https://openalex.org/W2293634267","https://openalex.org/W2397375888","https://openalex.org/W2406310406","https://openalex.org/W2513836842","https://openalex.org/W2891367150","https://openalex.org/W3028642772","https://openalex.org/W6600640353","https://openalex.org/W6601464659","https://openalex.org/W6601540304","https://openalex.org/W6601701123","https://openalex.org/W6602002150","https://openalex.org/W6607188615","https://openalex.org/W6638754818","https://openalex.org/W6696934422","https://openalex.org/W6712344080","https://openalex.org/W6713623370","https://openalex.org/W6777926273"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2351687372","https://openalex.org/W2314871050"],"abstract_inverted_index":{"This":[0,30],"article":[1],"presents":[2],"a":[3,16,70,145],"whisper":[4,46,81,90,137,158],"speech":[5],"detector":[6],"in":[7,45,87,110],"the":[8,63,76,107,128,167,176,179],"far-field":[9,43],"domain.":[10],"The":[11],"proposed":[12,108,180],"system":[13],"consists":[14],"of":[15,38,62,72,96,135,178],"long-short":[17],"term":[18],"memory":[19],"(LSTM)":[20],"neural":[21],"network":[22],"trained":[23,33],"on":[24,36,75],"log-filterbank":[25],"energy":[26],"(LFBE)":[27],"acoustic":[28],"features.":[29,182],"model":[31,130,148],"is":[32,131],"and":[34,47,83,103,153,159],"evaluated":[35],"recordings":[37],"human":[39],"interactions":[40],"with":[41,112,125,175],"voice-controlled,":[42],"devices":[44],"normal":[48,92,160],"phonation":[49],"modes.":[50],"We":[51,122],"compare":[52],"multiple":[53],"inference":[54],"approaches":[55],"for":[56,156],"utterance-level":[57],"classification":[58],"by":[59],"examining":[60],"trajectories":[61],"LSTM":[64,129,168],"posteriors.":[65],"In":[66,162],"addition,":[67,163],"we":[68,164],"engineer":[69],"set":[71],"features":[73,98,141,154],"based":[74],"signal":[77],"characteristics":[78,138],"inherent":[79],"to":[80,144],"speech,":[82],"evaluate":[84],"their":[85],"effectiveness":[86],"further":[88,118,173],"separating":[89,157],"from":[91,139],"speech.":[93,161],"A":[94],"benchmarking":[95],"these":[97],"using":[99],"multilayer":[100],"perceptrons":[101],"(MLP)":[102],"LSTMs":[104],"suggests":[105],"that":[106,149,166],"features,":[109,114],"combination":[111],"LFBE":[113,140,152],"can":[115,171],"help":[116],"us":[117],"improve":[119],"our":[120],"classifiers.":[121],"prove":[123,165],"that,":[124],"enough":[126],"data,":[127],"indeed":[132],"as":[133],"capable":[134],"learning":[136],"alone":[142],"compared":[143],"simpler":[146],"MLP":[147],"uses":[150],"both":[151],"engineered":[155,181],"classifiers":[169],"accuracy":[170],"be":[172],"improved":[174],"incorporation":[177]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}