{"id":"https://openalex.org/W2936559592","doi":"https://doi.org/10.1109/icassp.2019.8683244","title":"Speaker Agnostic Foreground Speech Detection from Audio Recordings in Workplace Settings from Wearable Recorders","display_name":"Speaker Agnostic Foreground Speech Detection from Audio Recordings in Workplace Settings from Wearable Recorders","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936559592","doi":"https://doi.org/10.1109/icassp.2019.8683244","mag":"2936559592"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683244","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":"conference-paper","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/A5039305462","display_name":"Amrutha Nadarajan","orcid":"https://orcid.org/0000-0001-6993-829X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amrutha Nadarajan","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth S. Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6765","last_page":"6769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8281638622283936},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.6098534464836121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5521411895751953},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5091978907585144},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.49139609932899475},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46722280979156494},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4409598410129547},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.43156033754348755},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4138604402542114},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.412229061126709},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3658181428909302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3058754801750183},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.27689898014068604},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09672549366950989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281638622283936},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.6098534464836121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5521411895751953},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5091978907585144},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.49139609932899475},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46722280979156494},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4409598410129547},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.43156033754348755},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4138604402542114},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.412229061126709},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3658181428909302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3058754801750183},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27689898014068604},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09672549366950989},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683244","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W76901566","https://openalex.org/W1591607137","https://openalex.org/W1686810756","https://openalex.org/W1869286832","https://openalex.org/W1946893126","https://openalex.org/W1963835294","https://openalex.org/W2016773549","https://openalex.org/W2085662862","https://openalex.org/W2098441927","https://openalex.org/W2098950531","https://openalex.org/W2101404574","https://openalex.org/W2108950108","https://openalex.org/W2128468130","https://openalex.org/W2131816934","https://openalex.org/W2150080223","https://openalex.org/W2157944106","https://openalex.org/W2304609584","https://openalex.org/W2406262283","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2768914963","https://openalex.org/W2889442725","https://openalex.org/W2962866211","https://openalex.org/W6603097216","https://openalex.org/W6637373629","https://openalex.org/W6675403883","https://openalex.org/W6713752823","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Audio-signal":[0],"acquisition":[1],"as":[2,14,157],"part":[3,19],"of":[4,20,49,67,79,83,88,125],"wearable":[5,38],"sensing":[6],"adds":[7],"an":[8],"important":[9],"dimension":[10],"for":[11,186],"applications":[12],"such":[13],"understanding":[15],"human":[16],"behaviors.":[17],"As":[18],"a":[21,104,112,122,158],"large":[22],"study":[23],"on":[24],"work":[25],"place":[26],"behaviours,":[27],"we":[28,102,138],"collected":[29,43,139],"audio":[30,41,59,72,126,153],"data":[31],"from":[32],"individual":[33],"hospital":[34],"staff":[35],"using":[36,121],"custom":[37],"recorders.":[39],"The":[40,148],"features":[42],"were":[44],"limited":[45,123],"to":[46,62,90,107,117,142,160,176],"preserve":[47],"privacy":[48,191],"the":[50,53,64,68,71,80,135,145,170,173],"interactions":[51],"in":[52,140,164,172],"hospital.":[54],"A":[55],"first":[56],"step":[57],"towards":[58],"processing":[60],"is":[61,76],"identify":[63],"foreground":[65,108,119],"speech":[66,178],"person":[69],"wearing":[70],"badge.":[73],"This":[74],"task":[75],"challenging":[77],"because":[78],"multi-party":[81],"nature":[82],"possible":[84],"ambulatory":[85],"interactions,":[86],"lack":[87],"access":[89],"speaker":[91],"information":[92],"and":[93,96,154],"varying":[94],"channel":[95],"ambient":[97],"conditions.":[98],"In":[99],"this":[100],"paper,":[101],"present":[103],"speaker-agnostic":[105],"approach":[106],"detection.":[109],"We":[110,128,167],"propose":[111],"convolutional":[113],"neural":[114],"network":[115],"model":[116],"predict":[118],"regions":[120],"set":[124],"features.":[127],"show":[129,183],"that":[130],"these":[131],"models":[132,163,171],"generalize":[133],"across":[134],"proxy":[136,149],"corpora":[137,150],"house":[141],"approximately":[143],"match":[144],"deployment":[146],"environment.":[147],"contained":[151],"full":[152],"was":[155],"used":[156],"test-bed":[159],"analyze":[161],"our":[162],"greater":[165],"detail.":[166],"also":[168],"evaluated":[169],"workplace":[174,188],"setting":[175],"measure":[177],"activity.":[179],"Our":[180],"experimental":[181],"results":[182],"promising":[184],"direction":[185],"analyzing":[187],"behaviors":[189],"with":[190],"protected":[192],"sensing.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
