{"id":"https://openalex.org/W4401609259","doi":"https://doi.org/10.1109/icasspw62465.2024.10626136","title":"The Royalflush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge","display_name":"The Royalflush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609259","doi":"https://doi.org/10.1109/icasspw62465.2024.10626136"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626136","doi":"https://doi.org/10.1109/icasspw62465.2024.10626136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626136","pdf_url":null,"source":{"id":"https://openalex.org/S7407085919","display_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.05498","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062412625","display_name":"Jingguang Tian","orcid":"https://orcid.org/0009-0000-0865-9422","observed_orcids":["https://orcid.org/0009-0000-0865-9422"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingguang Tian","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044063009","display_name":"Shuaishuai Ye","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuaishuai Ye","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028561597","display_name":"Shunfei Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunfei Chen","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Xiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Xiang","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100965490","display_name":"Zhaohui Yin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaohui Yin","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041446566","display_name":"Xinhui Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Hu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000141731","display_name":"Xinkang Xu","orcid":"https://orcid.org/0009-0001-3689-9156","observed_orcids":["https://orcid.org/0009-0001-3689-9156","https://orcid.org/0009-0003-2771-1398"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinkang Xu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4834,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60391341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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":0.00019999999494757503,"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/speaker-diarization","display_name":"speaker diarization","score":0.9430000185966492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7900000214576721},{"id":"https://openalex.org/keywords/multi-channel-speech","display_name":"multi-channel speech","score":0.7319999933242798},{"id":"https://openalex.org/keywords/multi-talker-speech","display_name":"multi-speaker speech","score":0.8190000057220459},{"id":"https://openalex.org/keywords/self-supervised-representations","display_name":"self-supervised representations","score":0.8820000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763862609863281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.756995439529419},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6147667169570923},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5276854038238525},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5196862816810608},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5081868171691895},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3992387652397156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32336342334747314},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07175600528717041}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626136","doi":"https://doi.org/10.1109/icasspw62465.2024.10626136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626136","pdf_url":null,"source":{"id":"https://openalex.org/S7407085919","display_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.05498","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05498","pdf_url":"https://arxiv.org/pdf/2405.05498","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.05498","doi":"https://doi.org/10.48550/arxiv.2405.05498","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.05498","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.05498","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05498","pdf_url":"https://arxiv.org/pdf/2405.05498","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401609259.pdf","grobid_xml":"https://content.openalex.org/works/W4401609259.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W3015199127","https://openalex.org/W3025260599","https://openalex.org/W3094706770","https://openalex.org/W3160799772","https://openalex.org/W3203407300","https://openalex.org/W4206908380","https://openalex.org/W4224916733","https://openalex.org/W4226390724","https://openalex.org/W4226419173","https://openalex.org/W4385823318","https://openalex.org/W4385825684","https://openalex.org/W4392903270","https://openalex.org/W6810587411"],"related_works":["https://openalex.org/W4401609213","https://openalex.org/W4401608975","https://openalex.org/W4401597658","https://openalex.org/W4401609106","https://openalex.org/W4390307038","https://openalex.org/W4401609756","https://openalex.org/W4386303026","https://openalex.org/W4415432662","https://openalex.org/W4389315135","https://openalex.org/W3007946293"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3],"system":[4],"submission":[5],"for":[6],"the":[7,40,49,53,83,100],"In-Car":[8],"Multi-Channel":[9],"Automatic":[10],"Speech":[11],"Recognition":[12],"(ICMC-ASR)":[13],"Challenge,":[14],"which":[15],"focuses":[16],"on":[17,52,82,99],"speaker":[18,34],"diarization":[19,35,41],"and":[20,88],"speech":[21,57],"recognition":[22],"in":[23],"complex":[24],"multi-speaker":[25],"scenarios.":[26],"To":[27],"address":[28],"these":[29,71],"challenges,":[30],"we":[31,59,73],"develop":[32],"end-to-end":[33,66],"models":[36],"that":[37],"notably":[38],"decrease":[39],"error":[42,77,94],"rate":[43,78,95],"(DER)":[44],"by":[45],"49.58%":[46],"compared":[47],"to":[48,64],"official":[50],"baseline":[51],"development":[54],"set.":[55,104],"For":[56],"recognition,":[58],"utilize":[60],"self-supervised":[61],"learning":[62],"representations":[63],"train":[65],"ASR":[67],"models.":[68],"By":[69],"integrating":[70],"models,":[72],"achieve":[74],"a":[75,89],"character":[76,93],"(CER)":[79],"of":[80,97],"16.93%":[81],"track":[84,101],"1":[85],"evaluation":[86,103],"set,":[87],"concatenated":[90],"minimum":[91],"permutation":[92],"(cpCER)":[96],"25.88%":[98],"2":[102]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-08-16T00:00:00"}