{"id":"https://openalex.org/W4387870226","doi":"https://doi.org/10.1109/mlsp55844.2023.10285948","title":"NAaLOSS: Rethinking the Objective of Speech Enhancement","display_name":"NAaLOSS: Rethinking the Objective of Speech Enhancement","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387870226","doi":"https://doi.org/10.1109/mlsp55844.2023.10285948"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10285948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5088927394","display_name":"Kuan-Hsun Ho","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":true,"raw_author_name":"Kuan-Hsun Ho","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102549216","display_name":"En-Lun Yu","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":"En-Lun Yu","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["National Chi Nan University,Department of Electrical Engineering,Nantou,Taiwan","Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Department of Electrical Engineering,Nantou,Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053222355","display_name":"Berlin Chen","orcid":"https://orcid.org/0000-0003-0693-8932"},"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,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088927394"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.7885,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71983665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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":0.9973999857902527,"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":0.6078370809555054},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5173699259757996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.510882556438446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3595576286315918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2818978428840637},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.055496543645858765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6078370809555054},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5173699259757996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.510882556438446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3595576286315918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2818978428840637},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.055496543645858765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10285948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1946152311","https://openalex.org/W1983108229","https://openalex.org/W2070696251","https://openalex.org/W2078528584","https://openalex.org/W2127851351","https://openalex.org/W2153384885","https://openalex.org/W2398042854","https://openalex.org/W2603567530","https://openalex.org/W2884797218","https://openalex.org/W2937998856","https://openalex.org/W2962892438","https://openalex.org/W2972412503","https://openalex.org/W3016220767","https://openalex.org/W3167533889","https://openalex.org/W3191448984","https://openalex.org/W4225309689","https://openalex.org/W4297841603","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6810203598"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"Reducing":[0],"noise":[1,59,94],"interference":[2],"is":[3],"crucial":[4],"for":[5],"automatic":[6],"speech":[7,17],"recognition":[8],"(ASR)":[9],"in":[10,29],"a":[11,34,48],"real-world":[12],"scenario.":[13],"However,":[14],"most":[15,106],"single-channel":[16],"enhancement":[18],"(SE)":[19],"generates":[20],"\u201dprocessing":[21],"artifacts\u201d":[22],"that":[23,98],"negatively":[24],"affect":[25],"ASR":[26,91,103],"performance.":[27],"Hence,":[28],"this":[30],"study,":[31],"we":[32,119],"suggest":[33],"Noise-":[35],"and":[36,58,70,116,124,126],"Artifacts-aware":[37],"loss":[38,54],"function,":[39],"NAaLoss,":[40],"to":[41,65],"ameliorate":[42],"the":[43,53,62,90,102,110],"influence":[44],"of":[45,55,89,105,112],"artifacts":[46,121],"from":[47],"novel":[49],"perspective.":[50],"NAaLoss":[51,80,99],"considers":[52],"estimation,":[56],"de-artifact,":[57],"ignorance,":[60],"enabling":[61],"learned":[63,78],"SE":[64,75,113],"individually":[66],"model":[67],"speech,":[68],"artifacts,":[69],"noise.":[71],"We":[72],"examine":[73],"two":[74,87],"models":[76],"(simple/advanced)":[77],"with":[79],"under":[81],"various":[82],"input":[83],"scenarios":[84],"(clean/noisy)":[85],"using":[86],"configurations":[88],"system":[92],"(with/without":[93],"robustness).":[95],"Experiments":[96],"reveal":[97],"significantly":[100],"improves":[101],"performance":[104],"setups":[107],"while":[108],"preserving":[109],"quality":[111],"toward":[114],"perception":[115],"intelligibility.":[117],"Furthermore,":[118],"visualize":[120],"through":[122],"waveforms":[123],"spectrograms,":[125],"explain":[127],"their":[128],"impact":[129],"on":[130],"ASR.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}