{"id":"https://openalex.org/W4221156109","doi":"https://doi.org/10.1109/icassp43922.2022.9747755","title":"Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data","display_name":"Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221156109","doi":"https://doi.org/10.1109/icassp43922.2022.9747755"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747755","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5101474723","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-4181-9285"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001511287","display_name":"Nana Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nana Hou","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619807","display_name":"Yuchen Hu","orcid":"https://orcid.org/0000-0002-0696-6434"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051975583","display_name":"Shashank Shirol","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashank Shirol","raw_affiliation_strings":["Manipal Institute of Technology,Manipal,India","Manipal Institute of Technology, Manipal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal Institute of Technology,Manipal,India","institution_ids":["https://openalex.org/I164861460"]},{"raw_affiliation_string":"Manipal Institute of Technology, Manipal, India","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4298","last_page":"4302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9994000196456909,"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/robustness","display_name":"Robustness (evolution)","score":0.8085567951202393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7887222766876221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7759369611740112},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6362674832344055},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5673519372940063},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.54173344373703},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.44649991393089294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4196138381958008},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41732552647590637},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4167556166648865},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41243910789489746},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3960353434085846},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37872791290283203},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.321865975856781},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08520093560218811}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8085567951202393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7887222766876221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759369611740112},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6362674832344055},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5673519372940063},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.54173344373703},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.44649991393089294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196138381958008},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41732552647590637},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4167556166648865},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41243910789489746},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3960353434085846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37872791290283203},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.321865975856781},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08520093560218811},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747755","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W1522301498","https://openalex.org/W1922655562","https://openalex.org/W2250499536","https://openalex.org/W2327501763","https://openalex.org/W2765811365","https://openalex.org/W2798991696","https://openalex.org/W2891138528","https://openalex.org/W2936774411","https://openalex.org/W2962824709","https://openalex.org/W2963250244","https://openalex.org/W2963539064","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3011500442","https://openalex.org/W3011871163","https://openalex.org/W3108316907","https://openalex.org/W3163418064","https://openalex.org/W3186546663","https://openalex.org/W4320013936","https://openalex.org/W6608710415","https://openalex.org/W6631190155","https://openalex.org/W6640090968","https://openalex.org/W6691605950","https://openalex.org/W6750782655","https://openalex.org/W6780903180","https://openalex.org/W6799474351"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2962707588","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2002243964","https://openalex.org/W2356426224","https://openalex.org/W2734909224","https://openalex.org/W2022538999"],"abstract_inverted_index":{"Noise-robust":[0],"speech":[1,12,67,79,98],"recognition":[2,80,99],"systems":[3],"require":[4],"large":[5],"amounts":[6],"of":[7,23,30,63,86,117],"training":[8],"data":[9,13,32,68,108],"including":[10],"noisy":[11,52,66,90,107],"and":[14],"corresponding":[15],"transcripts":[16],"to":[17,50,82],"achieve":[18],"state-of-the-art":[19],"performances":[20],"in":[21,37,115],"face":[22],"various":[24],"practical":[25],"environments.":[26],"However,":[27],"such":[28],"plenty":[29],"in-domain":[31,65],"is":[33,69],"not":[34],"always":[35],"available":[36],"the":[38,55,84,87,96,112],"real-life":[39],"world.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,74],"propose":[45,76],"a":[46,77],"generative":[47],"adversarial":[48],"network":[49],"simulate":[51],"spectrum":[53,57],"from":[54],"clean":[56],"(SimuGAN),":[58],"where":[59],"only":[60],"10":[61],"minutes":[62],"unparalleled":[64],"required":[70],"as":[71],"labels.":[72],"Furthermore,":[73],"also":[75],"dual-path":[78],"system":[81,88,100],"improve":[83],"robustness":[85],"under":[89],"conditions.":[91],"Experimental":[92],"results":[93],"show":[94],"that":[95],"proposed":[97],"achieves":[101],"7.3%":[102],"absolute":[103],"improvement":[104],"with":[105],"simulated":[106],"by":[109],"Simu-GAN":[110],"over":[111],"best":[113],"baseline":[114],"terms":[116],"word":[118],"error":[119],"rate":[120],"(WER).":[121]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}