{"id":"https://openalex.org/W4372260021","doi":"https://doi.org/10.1109/icassp49357.2023.10095577","title":"The NIO System for Audio-Visual Diarization and Recognition in MISP Challenge 2022","display_name":"The NIO System for Audio-Visual Diarization and Recognition in MISP Challenge 2022","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260021","doi":"https://doi.org/10.1109/icassp49357.2023.10095577"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095577","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5109577487","display_name":"Gaopeng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gaopeng Xu","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002972091","display_name":"Xianliang Wang","orcid":"https://orcid.org/0000-0003-3462-608X"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xianliang Wang","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043697130","display_name":"Sang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sang Wang","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010272559","display_name":"Junfeng Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junfeng Yuan","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416208","display_name":"Wei Guo","orcid":"https://orcid.org/0009-0001-5322-9816"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358968","display_name":"Jie Gao","orcid":"https://orcid.org/0000-0001-9501-7603"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jie Gao","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109577487"],"corresponding_institution_ids":["https://openalex.org/I4210092066"],"apc_list":null,"apc_paid":null,"fwci":1.0189,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74741784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9986000061035156,"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-diarisation","display_name":"Speaker diarisation","score":0.8734763860702515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993205785751343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7922360897064209},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47572973370552063},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46593064069747925},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4506710171699524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40376681089401245},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1090516448020935}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8734763860702515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993205785751343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7922360897064209},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47572973370552063},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46593064069747925},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4506710171699524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40376681089401245},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1090516448020935}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095577","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4224916606","https://openalex.org/W4297841834","https://openalex.org/W4372317224"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W2405439032","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2499802997","https://openalex.org/W2112059504"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"NIO":[3],"system":[4,47],"for":[5,39],"audio-visual":[6,27,41],"diarization":[7,30,43],"and":[8,32,44],"recognition":[9],"in":[10,63],"the":[11,49,61],"Multimodal":[12],"Information":[13],"Based":[14],"Speech":[15],"Processing":[16],"(MISP)":[17],"Challenge":[18],"2022.":[19],"In":[20],"our":[21],"system,":[22],"we":[23],"proposed":[24],"combining":[25],"end-to-end":[26],"neural":[28],"speaker":[29,37],"model":[31],"Channel-wise":[33],"Av-fusion":[34],"encoder":[35],"with":[36],"signature":[38],"multi-channel":[40],"speech":[42],"recognition.":[45],"Our":[46],"reduces":[48],"concatenated":[50],"minimum":[51],"permutation":[52],"character":[53],"error":[54],"rate(cpCER)":[55],"by":[56],"34.36%":[57],"absolute":[58],"compared":[59],"to":[60],"baseline":[62],"track":[64],"2.":[65]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
