{"id":"https://openalex.org/W4408353073","doi":"https://doi.org/10.1109/icassp49660.2025.10888086","title":"M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper","display_name":"M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353073","doi":"https://doi.org/10.1109/icassp49660.2025.10888086"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5114859604","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0009-0001-4760-9708"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113598702","display_name":"Jizhou He","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabei He","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460910","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0003-2161-0150"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenjia Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128622","display_name":"The People's Hospital of LinXia","ror":"https://ror.org/03k4zrh82","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128622"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjia Zeng","raw_affiliation_strings":["Lingxi (Beijing) Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lingxi (Beijing) Technology Co., Ltd","institution_ids":["https://openalex.org/I4210128622"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087985879","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0002-4241-1698"},"institutions":[{"id":"https://openalex.org/I4210128622","display_name":"The People's Hospital of LinXia","ror":"https://ror.org/03k4zrh82","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128622"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Lingxi (Beijing) Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lingxi (Beijing) Technology Co., Ltd","institution_ids":["https://openalex.org/I4210128622"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoqin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqin Sun","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aobo Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aobo Kong","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5114859604"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":12.8163,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98266162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7713000178337097,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7713000178337097,"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/computer-science","display_name":"Computer science","score":0.7313635349273682},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.523712694644928},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.4911639392375946},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.09943622350692749},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.04678064584732056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313635349273682},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.523712694644928},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.4911639392375946},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.09943622350692749},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04678064584732056},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":34,"referenced_works":["https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2998702515","https://openalex.org/W3097777922","https://openalex.org/W4221167707","https://openalex.org/W4280618630","https://openalex.org/W4287891464","https://openalex.org/W4293216099","https://openalex.org/W4297841687","https://openalex.org/W4372260310","https://openalex.org/W4375869316","https://openalex.org/W4385567149","https://openalex.org/W4385569885","https://openalex.org/W4385571264","https://openalex.org/W4385656656","https://openalex.org/W4388017359","https://openalex.org/W4392903240","https://openalex.org/W4392903872","https://openalex.org/W4392910591","https://openalex.org/W4392931630","https://openalex.org/W4402111964","https://openalex.org/W4402112225","https://openalex.org/W4406461303","https://openalex.org/W4408352239","https://openalex.org/W6770813465","https://openalex.org/W6783813245","https://openalex.org/W6803401863","https://openalex.org/W6847363464","https://openalex.org/W6849327941","https://openalex.org/W6850218400","https://openalex.org/W6852909395","https://openalex.org/W6857492710","https://openalex.org/W6861859833","https://openalex.org/W6873278751"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"State-of-the-art":[0],"models":[1],"like":[2],"OpenAI\u2019s":[3],"Whisper":[4],"exhibit":[5],"strong":[6],"performance":[7,42],"in":[8,19,43,62,118],"multilingual":[9],"automatic":[10],"speech":[11],"recognition":[12,102],"(ASR),":[13],"but":[14],"they":[15],"still":[16],"face":[17],"challenges":[18],"accurately":[20],"recognizing":[21],"diverse":[22],"subdialects.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"propose":[28],"M2R-Whisper,":[29],"a":[30,78],"novel":[31],"multi-stage":[32],"and":[33,54,92,108,113],"multi-scale":[34],"retrieval":[35,76,94],"augmentation":[36],"approach":[37],"designed":[38],"to":[39,66,81],"enhance":[40],"ASR":[41,119],"low-resource":[44],"settings.":[45],"Building":[46],"on":[47,106],"the":[48,63,84],"principles":[49],"of":[50,101],"in-context":[51],"learning":[52],"(ICL)":[53],"retrieval-augmented":[55],"techniques,":[56],"our":[57],"method":[58],"employs":[59],"sentence-level":[60,91],"ICL":[61],"pre-processing":[64],"stage":[65],"harness":[67],"contextual":[68],"information,":[69],"while":[70],"integrating":[71],"token-level":[72,93],"k-Nearest":[73],"Neighbors":[74],"(kNN)":[75],"as":[77],"post-processing":[79],"step":[80],"further":[82],"refine":[83],"final":[85],"output":[86],"distribution.":[87],"By":[88],"synergistically":[89],"combining":[90],"strategies,":[95],"M2R-Whisper":[96],"effectively":[97],"mitigates":[98],"various":[99],"types":[100],"errors.":[103],"Experiments":[104],"conducted":[105],"Mandarin":[107],"subdialect":[109],"datasets,":[110],"including":[111],"AISHELL-1":[112],"KeSpeech,":[114],"demonstrate":[115],"substantial":[116],"improvements":[117],"accuracy,":[120],"all":[121],"achieved":[122],"without":[123],"any":[124],"parameter":[125],"updates.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2025-10-10T00:00:00"}