{"id":"https://openalex.org/W4408352093","doi":"https://doi.org/10.1109/icassp49660.2025.10889088","title":"Advancing Non-intrusive Suppression on Enhancement Distortion for Noise Robust ASR","display_name":"Advancing Non-intrusive Suppression on Enhancement Distortion for Noise Robust ASR","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352093","doi":"https://doi.org/10.1109/icassp49660.2025.10889088"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889088","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":"conference-paper","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/A5100391971","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-4392-1884"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004652309","display_name":"Siyi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyi Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9559000134468079,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6676942706108093},{"id":"https://openalex.org/keywords/noise-suppression","display_name":"Noise suppression","score":0.6005738973617554},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5915186405181885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5910053253173828},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5742523074150085},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42148858308792114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3472668528556824},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.32333922386169434},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27625730633735657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2446901500225067},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16331598162651062},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1250171661376953},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12087199091911316},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.0947733223438263},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07421818375587463},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05419766902923584}],"concepts":[{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6676942706108093},{"id":"https://openalex.org/C2987345804","wikidata":"https://www.wikidata.org/wiki/Q583234","display_name":"Noise suppression","level":3,"score":0.6005738973617554},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5915186405181885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5910053253173828},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5742523074150085},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42148858308792114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3472668528556824},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.32333922386169434},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27625730633735657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2446901500225067},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16331598162651062},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1250171661376953},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12087199091911316},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0947733223438263},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07421818375587463},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05419766902923584},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889088","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":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1989034586","https://openalex.org/W2064675550","https://openalex.org/W2559260703","https://openalex.org/W2952218014","https://openalex.org/W2963242190","https://openalex.org/W2972320711","https://openalex.org/W2972436155","https://openalex.org/W2998161426","https://openalex.org/W2998616931","https://openalex.org/W3015199127","https://openalex.org/W3015312544","https://openalex.org/W3015372568","https://openalex.org/W3016056257","https://openalex.org/W3032514799","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3109196171","https://openalex.org/W3151851237","https://openalex.org/W3161950572","https://openalex.org/W3162315798","https://openalex.org/W3205533980","https://openalex.org/W4224938485","https://openalex.org/W4283067311","https://openalex.org/W4297841603","https://openalex.org/W4297841651","https://openalex.org/W4319586676","https://openalex.org/W4372259751","https://openalex.org/W4372260292","https://openalex.org/W4375928773","https://openalex.org/W4380434618","https://openalex.org/W4385822727","https://openalex.org/W4391021774","https://openalex.org/W4400877621","https://openalex.org/W4402111568","https://openalex.org/W6631190155","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W3002068412","https://openalex.org/W1585241115","https://openalex.org/W2120213246"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,14,29,47,64],"speech":[3,10,23],"enhancement":[4,38],"(SE)":[5],"techniques":[6],"have":[7,43],"greatly":[8],"improved":[9],"clarity":[11],"and":[12,108,131,137],"intelligibility":[13],"challenging":[15],"acoustic":[16],"environments.":[17],"However,":[18],"integrating":[19],"SE":[20,57,86,115,139],"into":[21],"automatic":[22],"recognition":[24,45],"(ASR)":[25],"systems":[26],"often":[27,51],"results":[28],"performance":[30,154],"degradation":[31],"due":[32],"to":[33],"artifacts":[34,82],"introduced":[35],"during":[36],"the":[37,85,101,106,118,148,153],"process.":[39],"While":[40],"various":[41,142],"methods":[42],"enhanced":[44,109],"accuracy":[46],"SE-ASR":[48,156],"systems,":[49,157],"they":[50],"require":[52],"fine-tuning":[53],"or":[54,58,87],"re-training":[55],"of":[56,105,155],"ASR":[59,88,133,143,164],"models,":[60,89],"which":[61],"is":[62],"impractical":[63],"many":[65],"real-world":[66],"applications.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"propose":[72],"a":[73],"lightweight":[74],"distortion":[75],"suppression":[76],"(DS)":[77],"network":[78],"that":[79,147],"addresses":[80],"these":[81],"without":[83],"modifying":[84],"treating":[90],"them":[91],"as":[92],"fixed":[93],"black":[94],"boxes.":[95],"The":[96],"DS":[97,149],"module":[98,150],"operates":[99],"on":[100,128],"time-frequency":[102],"(T-F)":[103],"bands":[104],"original":[107,119],"complex":[110],"spectrograms,":[111],"efficiently":[112],"compensating":[113],"for":[114],"distortions":[116],"using":[117,135],"T-F":[120],"information.":[121],"We":[122],"validate":[123],"our":[124],"approach":[125],"through":[126],"experiments":[127],"both":[129],"Mandarin":[130],"English":[132],"tasks":[134],"monaural":[136],"multi-channel":[138],"frontends,":[140],"across":[141],"backends.":[144,165],"Results":[145],"show":[146],"significantly":[151],"improves":[152],"even":[158],"when":[159],"used":[160],"with":[161],"robust":[162],"commercial":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}