{"id":"https://openalex.org/W2983262020","doi":"https://doi.org/10.1121/1.5137266","title":"Speaker tracking using SincNet for multi-channel naturalistic audio corpora: Apollo 11 fearless steps","display_name":"Speaker tracking using SincNet for multi-channel naturalistic audio corpora: Apollo 11 fearless steps","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2983262020","doi":"https://doi.org/10.1121/1.5137266","mag":"2983262020"},"language":"en","primary_location":{"id":"doi:10.1121/1.5137266","doi":"https://doi.org/10.1121/1.5137266","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5137266","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","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/A5047951089","display_name":"Meena Chandra Shekar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Meena Chandra Shekar","raw_affiliation_strings":["CRSS: Ctr. for Robust Speech Systems, Univ. of Texas at Dallas, 7220 McCallum Blvd, Apt. 1704, Dallas, TX 75252, Meena.ChandraShekar@utdallas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRSS: Ctr. for Robust Speech Systems, Univ. of Texas at Dallas, 7220 McCallum Blvd, Apt. 1704, Dallas, TX 75252, Meena.ChandraShekar@utdallas.edu","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["CRSS: Ctr. for Robust Speech Systems, Univ. of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRSS: Ctr. for Robust Speech Systems, Univ. of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047951089"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"146","issue":"4_Supplement","first_page":"2956","last_page":"2956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922000169754028,"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":0.9922000169754028,"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":0.005100000184029341,"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":0.0020000000949949026,"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/speaker-tracking","display_name":"speaker tracking","score":0.9929999709129333},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.8820000290870667},{"id":"https://openalex.org/keywords/sincnet","display_name":"SincNet","score":0.9860000014305115},{"id":"https://openalex.org/keywords/multichannel-audio","display_name":"multichannel audio","score":0.7720000147819519},{"id":"https://openalex.org/keywords/apollo-11","display_name":"Apollo 11","score":0.9829999804496765},{"id":"https://openalex.org/keywords/oral-communication","display_name":"oral communication","score":0.4560000002384186},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8510000109672546},{"id":"https://openalex.org/keywords/moon-landing","display_name":"lunar landing","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C2779821442","wikidata":"https://www.wikidata.org/wiki/Q41633","display_name":"Apollo","level":2,"score":0.951917827129364},{"id":"https://openalex.org/C25761169","wikidata":"https://www.wikidata.org/wiki/Q1757070","display_name":"Mission control center","level":2,"score":0.6472831964492798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6231269240379333},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5342147946357727},{"id":"https://openalex.org/C178802073","wikidata":"https://www.wikidata.org/wiki/Q8421","display_name":"Aeronautics","level":1,"score":0.49747827649116516},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.46302950382232666},{"id":"https://openalex.org/C152067771","wikidata":"https://www.wikidata.org/wiki/Q495307","display_name":"Moon landing","level":3,"score":0.4171901047229767},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16725119948387146},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C90856448","wikidata":"https://www.wikidata.org/wiki/Q431","display_name":"Zoology","level":1,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/1.5137266","doi":"https://doi.org/10.1121/1.5137266","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5137266","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4367595522","https://openalex.org/W3215101153","https://openalex.org/W4312744168","https://openalex.org/W2801846484","https://openalex.org/W4406147725","https://openalex.org/W2404649752","https://openalex.org/W2987108559","https://openalex.org/W4385822475","https://openalex.org/W4408353459","https://openalex.org/W7160946407"],"abstract_inverted_index":{"Apollo-11":[0,105,138],"was":[1],"the":[2,12,26,31,55,67,70,83,86,115,145,157,177],"first":[3],"manned":[4],"space":[5],"mission":[6],"to":[7,11,81,110,153,163,167,170],"successfully":[8],"bring":[9],"astronauts":[10,24,42],"moon":[13],"and":[14,61,120],"return":[15],"them":[16],"safely.":[17],"As":[18],"a":[19,91,99,128],"massive":[20],"collaborative":[21],"effort,":[22],"with":[23,176],"flying":[25],"missions":[27],"in":[28,69,85],"outer":[29],"space,":[30],"entire":[32],"communications":[33,52],"between":[34],"flight":[35],"controllers,":[36],"their":[37],"backroom":[38],"support":[39],"teams":[40],"and,":[41],"have":[43,72],"taken":[44],"place":[45],"inside":[46],"NASA":[47],"Mission":[48,87],"Control":[49,88],"Center.":[50],"The":[51,123,140],"stemming":[53],"from":[54,98,144],"experienced":[56],"team":[57],"of":[58,94,104,114,147],"scientists,":[59],"engineers,":[60],"technicians":[62],"who":[63],"worked":[64],"collectively":[65],"behind":[66],"scenes":[68],"MOCR":[71],"not":[73],"been":[74],"identified.":[75],"In":[76],"this":[77],"study,":[78],"we":[79],"propose":[80],"identify":[82],"speakers":[84,155],"Room":[89],"for":[90],"small":[92],"subset":[93,146],"100":[95,148],"h":[96,103],"derived":[97],"collective":[100],"19":[101],"000":[102],"audio":[106],"data,":[107],"which":[108],"correspond":[109],"three":[111,137],"challenging":[112],"phases":[113],"mission:":[116],"lift-off,":[117],"lunar":[118,121],"landing,":[119],"walking.":[122],"speaker":[124,141,174],"identification":[125],"solution":[126],"explores":[127],"convolutional":[129],"neural":[130],"network":[131],"architecture":[132],"called":[133],"SincNet":[134],"across":[135],"all":[136],"phases.":[139],"models":[142],"obtained":[143],"hours":[149],"will":[150],"be":[151,168],"used":[152],"track":[154],"on":[156],"complete":[158],"corpora.":[159],"Our":[160],"goal":[161],"is":[162],"make":[164],"it":[165],"possible":[166],"able":[169],"access":[171],"each":[172],"individual":[173],"involved":[175],"Apollo":[178],"11":[179],"mission.":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-11-22T00:00:00"}