{"id":"https://openalex.org/W4401878432","doi":"https://doi.org/10.1109/lsp.2024.3449218","title":"MC-Whisper: Extending Speech Foundation Models to Multichannel Distant Speech Recognition","display_name":"MC-Whisper: Extending Speech Foundation Models to Multichannel Distant Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401878432","doi":"https://doi.org/10.1109/lsp.2024.3449218"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3449218","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2024.3449218","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"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":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5221-5412","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0001-2388-5935","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003520396","display_name":"Y Fujita","orcid":"https://orcid.org/0009-0003-9170-0335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["LY Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0003-9170-0335","affiliations":[{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":["LY Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","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, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1139744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"2850","last_page":"2854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8745999932289124,"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":0.8745999932289124,"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":0.8729000091552734,"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":0.7205816507339478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6952368021011353},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.41937369108200073},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41652870178222656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3611530661582947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205816507339478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6952368021011353},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.41937369108200073},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41652870178222656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3611530661582947},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3449218","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2024.3449218","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2895727626","display_name":null,"funder_award_id":"tel:2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3725712410","display_name":null,"funder_award_id":"tel:2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4006316252","display_name":"Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS)","funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6027080096","display_name":null,"funder_award_id":"tel:2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8497556401","display_name":null,"funder_award_id":"tel:2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1982728343","https://openalex.org/W1983812858","https://openalex.org/W2042141988","https://openalex.org/W2060108923","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2160815625","https://openalex.org/W2168729028","https://openalex.org/W2242685705","https://openalex.org/W2398042854","https://openalex.org/W2515753980","https://openalex.org/W2517616541","https://openalex.org/W2559809918","https://openalex.org/W2640112133","https://openalex.org/W2760287881","https://openalex.org/W2939497224","https://openalex.org/W2939777271","https://openalex.org/W2962780374","https://openalex.org/W2982471419","https://openalex.org/W3020336359","https://openalex.org/W3086154751","https://openalex.org/W3168719366","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225310539","https://openalex.org/W4281492411","https://openalex.org/W4319862214","https://openalex.org/W4323066695","https://openalex.org/W4372342485","https://openalex.org/W4385822321","https://openalex.org/W4388017359","https://openalex.org/W4389315128","https://openalex.org/W4391021675","https://openalex.org/W4392909789","https://openalex.org/W6623517193","https://openalex.org/W6735168207","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6847363464","https://openalex.org/W6850218400"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Distant":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(DASR)":[4],"stands":[5],"as":[6,124],"a":[7,63,119,125],"crucial":[8],"aspect":[9],"in":[10,35,54,76,85],"the":[11,22,36,86,92,102,109,129,132,143,156],"realm":[12],"of":[13,24,44,46,48,70,104,131],"speech":[14,26,49,80,121,146],"and":[15,56],"audio":[16],"processing.":[17],"Recent":[18],"advancements":[19],"have":[20],"spotlighted":[21],"efficacy":[23],"pre-trained":[25,110],"foundation":[27,133],"models,":[28,40],"exemplified":[29],"by":[30,100],"Whisper,":[31],"garnering":[32],"considerable":[33],"attention":[34],"speech-processing":[37],"domain.":[38],"These":[39],"trained":[41],"on":[42,142],"hundreds":[43],"thousands":[45],"hours":[47],"data,":[50],"exhibit":[51],"notable":[52],"strengths":[53],"performance":[55],"generalization":[57],"across":[58],"various":[59],"zero-shot":[60],"scenarios.":[61],"However,":[62],"limitation":[64],"arises":[65],"from":[66,148],"their":[67],"exclusive":[68],"handling":[69],"single-channel":[71],"input":[72,88],"due":[73],"to":[74,127,136],"challenges":[75],"accumulating":[77],"extensive":[78],"multi-channel":[79,87,105,120,138],"data.":[81],"The":[82,115],"spatial":[83],"information":[84],"is":[89],"important":[90],"for":[91],"DASR":[93],"task.":[94],"This":[95],"study":[96],"introduces":[97,118],"an":[98],"innovation":[99],"enabling":[101],"incorporation":[103],"(MC)":[106],"signals":[107],"into":[108],"Whisper":[111],"model,":[112],"called":[113],"MC-Whisper.":[114],"proposed":[116,157],"model":[117],"processing":[122],"branch":[123],"sidecar,":[126],"maximize":[128],"utilization":[130],"model's":[134],"ability":[135],"handle":[137],"input.":[139],"Experimental":[140],"results":[141],"distant":[144],"microphone":[145],"recordings":[147],"AMI":[149],"meeting":[150],"corpus":[151],"demonstrate":[152],"substantial":[153],"improvements":[154],"through":[155],"approach.":[158]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
