{"id":"https://openalex.org/W4392902861","doi":"https://doi.org/10.1109/icassp48485.2024.10446231","title":"Apollo\u2019s Unheard Voices: Graph Attention Networks for Speaker Diarization and Clustering for Fearless Steps Apollo Collection","display_name":"Apollo\u2019s Unheard Voices: Graph Attention Networks for Speaker Diarization and Clustering for Fearless Steps Apollo Collection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902861","doi":"https://doi.org/10.1109/icassp48485.2024.10446231"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5059065485","display_name":"Meena M. C. Shekar","orcid":null},"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":"Meena M. C. Shekar","raw_affiliation_strings":["The University of Texas at Dallas,Center for Robust Speech Systems,USA","Center for Robust Speech Systems, The University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Center for Robust Speech Systems,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems, The University of Texas at Dallas, USA","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"},"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":["The University of Texas at Dallas,Center for Robust Speech Systems,USA","Center for Robust Speech Systems, The University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Center for Robust Speech Systems,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems, The University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11881","last_page":"11885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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":0.785130500793457},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7264493107795715},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6154187917709351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5614733695983887},{"id":"https://openalex.org/keywords/apollo","display_name":"Apollo","score":0.55191570520401},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5003321170806885},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.44596612453460693},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43694767355918884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35956814885139465},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.29033124446868896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785130500793457},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7264493107795715},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6154187917709351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5614733695983887},{"id":"https://openalex.org/C2779821442","wikidata":"https://www.wikidata.org/wiki/Q41633","display_name":"Apollo","level":2,"score":0.55191570520401},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5003321170806885},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.44596612453460693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43694767355918884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35956814885139465},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29033124446868896},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2101234009","https://openalex.org/W2750259098","https://openalex.org/W2972869740","https://openalex.org/W3016021376","https://openalex.org/W3024869864","https://openalex.org/W3097636940","https://openalex.org/W3167533889","https://openalex.org/W3198793808","https://openalex.org/W4286795917","https://openalex.org/W4288419263","https://openalex.org/W4292794006","https://openalex.org/W4297733535","https://openalex.org/W4367595522","https://openalex.org/W4372342420","https://openalex.org/W4385822475","https://openalex.org/W4387068218","https://openalex.org/W6726873649","https://openalex.org/W6745537798","https://openalex.org/W6779715462"],"related_works":["https://openalex.org/W2054178368","https://openalex.org/W2001637022","https://openalex.org/W2749643947","https://openalex.org/W2921637885","https://openalex.org/W4244081656","https://openalex.org/W2981806746","https://openalex.org/W4400809088","https://openalex.org/W2148601393","https://openalex.org/W2937293962","https://openalex.org/W2935892485"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,105,176],"has":[2],"traditionally":[3],"been":[4],"explored":[5],"using":[6,114,130],"datasets":[7],"that":[8,50],"are":[9],"either":[10],"clean,":[11],"feature":[12],"a":[13,20,35,47,87,102,121,164],"limited":[14],"number":[15,89],"of":[16,23,29,55,63,79,90,126,174],"speakers,":[17],"or":[18],"have":[19],"large":[21],"volume":[22],"data":[24,49,57,84,115],"but":[25],"lack":[26],"the":[27,41,61,139,149,172],"complexities":[28],"real-world":[30,182],"scenarios.":[31,183],"This":[32,67,160],"study":[33],"takes":[34],"unique":[36],"approach":[37],"by":[38],"focusing":[39],"on":[40,108,148],"Fearless":[42],"Steps":[43],"APOLLO":[44],"audio":[45,56],"resource,":[46],"challenging":[48,181],"contains":[51],"over":[52],"70,000":[53],"hours":[54],"(A-11:":[58],"10k":[59],"hrs),":[60],"majority":[62],"which":[64],"remains":[65],"unlabeled.":[66],"corpus":[68],"presents":[69],"considerable":[70],"challenges":[71],"such":[72],"as":[73,163],"diverse":[74],"acoustic":[75],"conditions,":[76],"high":[77],"levels":[78],"background":[80],"noise,":[81],"overlapping":[82],"speech,":[83],"imbalance,":[85],"and":[86,144,171],"variable":[88],"speakers":[91,154],"with":[92],"varying":[93],"utterance":[94],"duration.":[95],"To":[96],"address":[97],"these":[98],"challenges,":[99],"we":[100],"propose":[101],"robust":[103,175],"speaker":[104],"framework":[106,119],"built":[107],"dynamic":[109],"Graph":[110],"Attention":[111],"Network":[112],"optimized":[113],"augmentation.":[116],"Our":[117],"proposed":[118],"attains":[120],"Diarization":[122],"Error":[123],"Rate":[124],"(DER)":[125],"19.6%":[127],"when":[128],"evaluated":[129],"ground":[131],"truth":[132],"speech":[133],"segments.":[134],"Notably,":[135],"our":[136],"work":[137,161],"is":[138],"first":[140],"to":[141,167],"recognize,":[142],"track,":[143],"perform":[145],"conversational":[146],"analysis":[147],"entire":[150],"Apollo-11":[151],"mission":[152],"for":[153,180],"who":[155],"were":[156],"unidentified":[157],"until":[158],"now.":[159],"stands":[162],"significant":[165],"contribution":[166],"both":[168],"historical":[169],"archiving":[170],"development":[173],"systems,":[177],"particularly":[178],"relevant":[179]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}