{"id":"https://openalex.org/W4392903890","doi":"https://doi.org/10.1109/icassp48485.2024.10446300","title":"VoxMM: Rich Transcription of Conversations in the Wild","display_name":"VoxMM: Rich Transcription of Conversations in the Wild","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903890","doi":"https://doi.org/10.1109/icassp48485.2024.10446300"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446300","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":"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/A5113379249","display_name":"Doyeop Kwak","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Doyeop Kwak","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000060266","display_name":"Jaemin Jung","orcid":"https://orcid.org/0000-0002-6815-7763"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Jaemin Jung","raw_affiliation_strings":["Carnegie Mellon University,USA","Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102335705","display_name":"Ki-Hyun Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kihyun Nam","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013499323","display_name":"Youngjoon Jang","orcid":"https://orcid.org/0009-0002-0500-6025"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoon Jang","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Jee-Weon Jung","raw_affiliation_strings":["Carnegie Mellon University,USA","Korea Advanced Institute of Science and Technology,South Korea","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113379249"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.3171,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82367092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12551","last_page":"12555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9991000294685364,"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/metadata","display_name":"Metadata","score":0.8391745090484619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8318214416503906},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7434885501861572},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6576204299926758},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6115111112594604},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5771376490592957},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5182866454124451},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5015146732330322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49363434314727783},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42141368985176086},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40512487292289734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39610785245895386},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17088624835014343}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8391745090484619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318214416503906},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7434885501861572},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6576204299926758},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6115111112594604},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5771376490592957},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5182866454124451},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5015146732330322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49363434314727783},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42141368985176086},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40512487292289734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39610785245895386},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17088624835014343},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446300","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":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8472331835","display_name":null,"funder_award_id":"2022-0-00989","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1591607137","https://openalex.org/W2029199293","https://openalex.org/W2035890032","https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2915347754","https://openalex.org/W2972449503","https://openalex.org/W2973127116","https://openalex.org/W2995181338","https://openalex.org/W3015598461","https://openalex.org/W3016098309","https://openalex.org/W3020336359","https://openalex.org/W3038871978","https://openalex.org/W3091427154","https://openalex.org/W3097777922","https://openalex.org/W3109496323","https://openalex.org/W3119308075","https://openalex.org/W3157070662","https://openalex.org/W3162293946","https://openalex.org/W3178462146","https://openalex.org/W3196595845","https://openalex.org/W3197331597","https://openalex.org/W3198482860","https://openalex.org/W3198694222","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W4286378963","https://openalex.org/W4297841641","https://openalex.org/W6743555153","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6799174933"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2361861616","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2263699433","https://openalex.org/W2106424170","https://openalex.org/W2377979023","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,22,62,76,93,122],"multi-modal":[4,15,26],"dataset":[5,40,73,156],"that":[6,41,65],"contains":[7],"rich":[8,33],"transcriptions":[9],"of":[10,54,89,96,114,126],"spoken":[11],"conversations.":[12],"As":[13],"diverse":[14,47],"and":[16,28,84,104,111,136,151],"multi-task":[17],"models":[18],"emerge,":[19],"there":[20,36],"is":[21,37,74],"growing":[23],"need":[24],"for":[25,45],"training":[27,110],"evaluation":[29,113],"datasets":[30],"accompanied":[31],"by":[32],"metadata.":[34],"However,":[35],"no":[38],"universal":[39],"addresses":[42],"these":[43],"requirements":[44],"the":[46,52,67,109,112,130,137,141],"tasks":[48],"partially":[49],"due":[50],"to":[51],"cost":[53],"annotation.":[55],"To":[56],"overcome":[57],"this":[58],"limitation,":[59],"we":[60],"develop":[61],"semi-automatic":[63],"pipeline":[64],"makes":[66],"annotation":[68],"more":[69,123],"feasible.":[70],"The":[71,154],"resulting":[72],"VoxMM,":[75],"multi-modal,":[77],"multi-domain":[78],"dataset.":[79],"VoxMM":[80,106,155],"incorporates":[81],"video,":[82],"audio,":[83],"text":[85],"modalities.":[86],"In":[87],"terms":[88],"labels,":[90,101],"it":[91],"offers":[92,121],"wide":[94],"array":[95],"metadata":[97],"such":[98],"as":[99],"speaker":[100,152],"transcriptions,":[102],"gender,":[103],"more.":[105],"supports":[107],"both":[108],"any-to-any":[115],"modality":[116],"mapping":[117],"models.":[118],"It":[119],"also":[120],"accurate":[124],"representation":[125],"real-world":[127],"scenarios,":[128],"bridging":[129],"gap":[131],"between":[132],"controlled":[133],"laboratory":[134],"experiments":[135],"varying":[138],"performances":[139],"in":[140],"real-world.":[142],"We":[143],"present":[144],"initial":[145],"benchmarks":[146],"on":[147],"automatic":[148],"speech":[149],"recognition":[150],"diarisation.":[153],"can":[157],"be":[158],"downloaded":[159],"from":[160],"https://mm.kaist.ac.kr/projects/voxmm":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
