{"id":"https://openalex.org/W7148465105","doi":"https://doi.org/10.1109/asru65441.2025.11434673","title":"Revealing the Role of Audio Channels in ASR Performance Degradation","display_name":"Revealing the Role of Audio Channels in ASR Performance Degradation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148465105","doi":"https://doi.org/10.1109/asru65441.2025.11434673"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5102841009","display_name":"Kui Huang","orcid":"https://orcid.org/0009-0005-5411-581X"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kuan-Tang Huang","raw_affiliation_strings":["National Taiwan Normal University,,Dept. Computer Science and Information Engineering,,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,,Dept. Computer Science and Information Engineering,,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108832513","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0003-4160-9771"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["National Tsing Hua University,,Dept. Computer Science and Information Engineering,,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,,Dept. Computer Science and Information Engineering,,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[{"id":"https://openalex.org/I4210136767","display_name":"Link Institut (Switzerland)","ror":"https://ror.org/04vhpaz11","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210136767"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["United Link Co., Ltd.,,Taiwan"],"affiliations":[{"raw_affiliation_string":"United Link Co., Ltd.,,Taiwan","institution_ids":["https://openalex.org/I4210136767"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800680","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,,Dept. Computer Science and Information Engineering,,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,,Dept. Computer Science and Information Engineering,,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132804366","display_name":"Hsin-Min Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130467","display_name":"Institute of Taiwan History, Academia Sinica","ror":"https://ror.org/02vf41z82","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210130467","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Computer Science,,Academia Sinica,,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science,,Academia Sinica,,Taiwan","institution_ids":["https://openalex.org/I4210130467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102841009"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87569034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8974000215530396,"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":0.8974000215530396,"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":0.03420000150799751,"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/T10863","display_name":"Voice and Speech Disorders","score":0.010099999606609344,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5626999735832214},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5210999846458435},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4957999885082245},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.3871999979019165},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.3716999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067999839782715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6635000109672546},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5626999735832214},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.502448558807373}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2937484199","https://openalex.org/W2973220283","https://openalex.org/W3097777922","https://openalex.org/W3097945073","https://openalex.org/W3204696009","https://openalex.org/W4297841603","https://openalex.org/W4312570973","https://openalex.org/W4312884055","https://openalex.org/W4313225456","https://openalex.org/W4387870226","https://openalex.org/W4389524317","https://openalex.org/W4392909075","https://openalex.org/W4392909789","https://openalex.org/W4393406219","https://openalex.org/W4400877621","https://openalex.org/W4402115972","https://openalex.org/W4404577030","https://openalex.org/W4408354843"],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"automatic":[1],"speech":[2,55],"recognition":[3],"(ASR)":[4],"models":[5],"have":[6,33],"demonstrated":[7,34],"strong":[8],"performance":[9,17,106],"on":[10,107],"a":[11,73,97],"variety":[12],"of":[13,81],"tasks.":[14],"However,":[15],"their":[16],"can":[18,62],"degrade":[19],"substantially":[20],"when":[21],"the":[22,42,79,90],"input":[23],"audio":[24],"comes":[25],"from":[26,96],"different":[27,59],"recording":[28,60],"channels.":[29],"While":[30],"previous":[31],"studies":[32],"this":[35,69],"phenomenon,":[36],"it":[37],"is":[38],"often":[39],"attributed":[40],"to":[41,77,116],"mismatch":[43],"between":[44],"training":[45],"and":[46,111,120],"testing":[47],"corpora.":[48],"This":[49,101],"study":[50],"argues":[51],"that":[52],"variations":[53],"in":[54,89],"characteristics":[56],"caused":[57],"by":[58,84],"channels":[61,110],"fundamentally":[63],"harm":[64],"ASR":[65,91,105],"performance.":[66],"To":[67],"address":[68],"limitation,":[70],"we":[71],"propose":[72],"normalization":[74],"technique":[75],"designed":[76],"mitigate":[78],"impact":[80],"channel":[82,119],"variation":[83],"aligning":[85],"internal":[86],"feature":[87],"representations":[88],"model":[92],"with":[93],"those":[94],"derived":[95],"clean":[98],"reference":[99],"channel.":[100],"approach":[102],"significantly":[103],"improves":[104],"previously":[108],"unseen":[109],"languages,":[112],"highlighting":[113],"its":[114],"ability":[115],"generalize":[117],"across":[118],"language":[121],"differences.":[122]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
