{"id":"https://openalex.org/W4401609106","doi":"https://doi.org/10.1109/icasspw62465.2024.10625781","title":"The Fosafer System for The ICASSP2024 In-Car Multi-Channel Automatic Speech Recognition Challenge","display_name":"The Fosafer System for The ICASSP2024 In-Car Multi-Channel Automatic Speech Recognition Challenge","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609106","doi":"https://doi.org/10.1109/icasspw62465.2024.10625781"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10625781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10625781","pdf_url":null,"source":null,"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"},"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/A5113335993","display_name":"Shangkun Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shangkun Huang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011431550","display_name":"Yuxuan Du","orcid":"https://orcid.org/0000-0002-5997-7882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Du","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111291985","display_name":"Yankai Wang","orcid":"https://orcid.org/0009-0006-6400-4571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yankai Wang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727973","display_name":"Jing Deng","orcid":"https://orcid.org/0000-0003-4032-0482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Deng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057928430","display_name":"Rong Zheng","orcid":"https://orcid.org/0000-0001-8829-0417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Zheng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113335993"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75421447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9897000193595886,"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":0.9897000193595886,"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":0.988099992275238,"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":0.7353223562240601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6977159380912781},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45089343190193176},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4421904683113098},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15357419848442078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353223562240601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6977159380912781},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45089343190193176},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4421904683113098},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15357419848442078}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10625781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10625781","pdf_url":null,"source":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3097777922","https://openalex.org/W3160799772","https://openalex.org/W4221149546","https://openalex.org/W4226390724","https://openalex.org/W4385822353","https://openalex.org/W4401608975","https://openalex.org/W6860682793"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,7,20,51,65],"Fosafer\u2019s":[4],"submissions":[5],"to":[6],"ICASSP":[8],"2024":[9],"In-Car":[10],"Multi-Channel":[11],"Automatic":[12,21,26],"Speech":[13,22,27],"Recognition":[14,23,30],"Challenge":[15],"(ICMC-ASR),":[16],"which":[17],"includes":[18],"both":[19],"(ASR)":[24],"and":[25,29,46,63],"Diarization":[28],"(ASDR)":[31],"systems.":[32],"In":[33,54],"Track1,":[34],"a":[35],"robust":[36],"ASR":[37],"system":[38],"with":[39],"data":[40],"augmentation,":[41],"self-supervised":[42],"learning":[43],"representation":[44],"(SSLR),":[45],"speech":[47],"enhancement":[48],"(SE)":[49],"achieved":[50,64],"second":[52],"place.":[53,67],"Track2,":[55],"different":[56],"speaker":[57],"diarization":[58],"algorithms":[59],"were":[60],"fully":[61],"exploited":[62],"fifth":[66]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}