{"id":"https://openalex.org/W2988489017","doi":"https://doi.org/10.1121/1.5137268","title":"Fearless steps: Taking the next step towards advanced speech technology for naturalistic audio","display_name":"Fearless steps: Taking the next step towards advanced speech technology for naturalistic audio","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2988489017","doi":"https://doi.org/10.1121/1.5137268","mag":"2988489017"},"language":"en","primary_location":{"id":"doi:10.1121/1.5137268","doi":"https://doi.org/10.1121/1.5137268","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5137268","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/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":true,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Dept. of Elec. and Comput. Eng., The Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Elec. and Comput. Eng., The Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088979748","display_name":"Aditya Joglekar","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":false,"raw_author_name":"Aditya Joglekar","raw_affiliation_strings":["Dept. of Elec. and Comput. Eng., The Univ. of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Elec. and Comput. Eng., The Univ. of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469714","display_name":"Abhijeet Sangwan","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":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":["Dept. of Elec. and Comput. Eng., The Univ. of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Elec. and Comput. Eng., The Univ. of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040951732","display_name":"Chengzhu Yu","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":false,"raw_author_name":"Chengzhu Yu","raw_affiliation_strings":["Dept. of Elec. and Comput. Eng., The Univ. of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Elec. and Comput. Eng., The 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/A5057910370"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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":0.006099999882280827,"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/T12031","display_name":"Speech and dialogue systems","score":0.0012000000569969416,"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/multi-talker-speech","display_name":"multi-speaker speech","score":0.7710000276565552},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"voice activity detection","score":0.6230000257492065},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9829999804496765},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.9760000109672546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9710000157356262},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"sentiment analysis","score":0.9649999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894318103790283},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6170692443847656},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.552643895149231},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.5409039855003357},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5384914875030518},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48464566469192505},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4686505198478699},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40272676944732666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3394257426261902},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3066651225090027},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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:10.1121/1.5137268","doi":"https://doi.org/10.1121/1.5137268","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5137268","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3049098931","https://openalex.org/W2801846484","https://openalex.org/W4312916150","https://openalex.org/W4320855191","https://openalex.org/W3047219644","https://openalex.org/W4408395457","https://openalex.org/W7140183942","https://openalex.org/W4392902861","https://openalex.org/W2889041236","https://openalex.org/W7160946407"],"abstract_inverted_index":{"Over":[0],"the":[1,14,57,66,69,104,113,155,184,197],"past":[2,58],"two":[3],"decades,":[4],"machine":[5],"learning":[6],"technologies":[7],"have":[8,24],"been":[9,25],"targeting":[10],"real-world":[11],"problems":[12],"in":[13,35,110,150,173,201],"Speech-Language":[15],"(SLT)":[16],"domain.":[17],"Speech":[18,165],"corpora":[19],"developed":[20],"under":[21],"diverse":[22],"environments":[23],"paramount":[26],"to":[27,77,129,147],"progress,":[28],"though":[29],"most":[30],"are":[31],"simulated/controlled":[32],"scenarios.":[33],"Success":[34],"Machine":[36],"Learning":[37],"for":[38],"SLT":[39],"requires":[40],"new":[41],"innovative":[42],"challenges":[43],"posed":[44],"by":[45],"multi-speaker":[46],"naturalistic":[47],"audio.":[48],"The":[49,82],"UTDallas-CRSS":[50],"led":[51],"Fearless":[52,70,106],"Steps":[53,71,107],"(FS)":[54],"initiative":[55,88,186],"over":[56,174,192],"6":[59],"years":[60],"has":[61],"made":[62,126],"significant":[63],"strides":[64],"through":[65,86,97],"development":[67],"of":[68,115,119,136,154,196],"Corpus,":[72],"and":[73,123,163,167,190,211],"multiple":[74],"novel":[75,179],"schemes":[76],"address":[78],"core":[79,157],"speech":[80,158,213],"tasks.":[81],"next":[83],"steps":[84],"taken":[85],"this":[87],"aim":[89],"at":[90,188],"motivating":[91],"further":[92],"research":[93],"on":[94,152,208],"these":[95],"data":[96,122,139],"worldwide":[98,177],"collaborative":[99],"efforts.":[100],"To":[101],"achieve":[102],"this,":[103],"Inaugural":[105],"Challenge":[108,144,171,205],"held":[109],"2019":[111],"saw":[112],"release":[114],"11":[116],"000":[117,194],"h":[118,135,195],"Apollo-11":[120],"audio":[121],"diarization":[124],"transcripts,":[125],"freely":[127],"available":[128,146],"public":[130],"online.":[131],"An":[132],"additional":[133],"100":[134],"manually":[137],"annotated":[138],"was":[140],"released":[141],"as":[142],"a":[143],"corpus,":[145],"researchers":[148],"interested":[149],"working":[151],"any":[153],"five":[156],"tasks:":[159],"Speech-Activity-Detection,":[160],"Speaker":[161],"Diarization":[162],"Identification,":[164],"Recognition,":[166],"Sentiment":[168],"Detection.":[169],"FS":[170,185],"resulted":[172],"150":[175,193],"participants":[176],"developing":[178,209],"task-specific":[180],"algorithms.":[181],"Going":[182],"forward,":[183],"aims":[187],"digitizing":[189],"releasing":[191],"remaining":[198],"Apollo":[199],"Missions":[200],"conjunction":[202],"with":[203],"follow-on":[204],"Tasks":[206],"focused":[207],"multi-channel":[210],"conversational":[212],"systems.":[214]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-11-22T00:00:00"}
