{"id":"https://openalex.org/W4375869169","doi":"https://doi.org/10.1109/icassp49357.2023.10096985","title":"Cross-Domain Diffusion Based Speech Enhancement for Very Noisy Speech","display_name":"Cross-Domain Diffusion Based Speech Enhancement for Very Noisy Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869169","doi":"https://doi.org/10.1109/icassp49357.2023.10096985","pmid":"https://pubmed.ncbi.nlm.nih.gov/40330790"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12051501/pdf/nihms-2076296.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101497068","display_name":"Heming Wang","orcid":"https://orcid.org/0000-0003-3057-9060"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heming Wang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2023","issue":null,"first_page":"1","last_page":"5"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/timit","display_name":"TIMIT","score":0.878575325012207},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8477476835250854},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.815297544002533},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.786130964756012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701597213745117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6659398674964905},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4802256226539612},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4556075632572174},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.45100533962249756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43939000368118286},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.42454713582992554},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4175885319709778},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2731226682662964},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.24300262331962585},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08530256152153015},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06039541959762573}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.878575325012207},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8477476835250854},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.815297544002533},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.786130964756012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701597213745117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6659398674964905},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4802256226539612},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4556075632572174},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.45100533962249756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43939000368118286},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.42454713582992554},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4175885319709778},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2731226682662964},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.24300262331962585},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08530256152153015},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06039541959762573},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:40330790","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40330790","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12051501","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12051501","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12051501/pdf/nihms-2076296.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12051501","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12051501","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12051501/pdf/nihms-2076296.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G6100668328","display_name":null,"funder_award_id":"DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375869169.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1974387177","https://openalex.org/W2006129368","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2141998673","https://openalex.org/W2803417661","https://openalex.org/W2991361823","https://openalex.org/W3015526955","https://openalex.org/W3032514799","https://openalex.org/W3036167779","https://openalex.org/W3094199623","https://openalex.org/W3096408984","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3157804362","https://openalex.org/W3158762648","https://openalex.org/W3162926177","https://openalex.org/W3172617364","https://openalex.org/W3197334236","https://openalex.org/W3199003182","https://openalex.org/W4205664022","https://openalex.org/W4233392025","https://openalex.org/W4253928870","https://openalex.org/W4293327156","https://openalex.org/W4385245566","https://openalex.org/W4387195417","https://openalex.org/W6631190155","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783890765","https://openalex.org/W6795261426","https://openalex.org/W6795288823","https://openalex.org/W6797095309","https://openalex.org/W6842958722"],"related_works":["https://openalex.org/W4375869169","https://openalex.org/W1980604799","https://openalex.org/W2597829360","https://openalex.org/W2921661700","https://openalex.org/W2138406058","https://openalex.org/W2153897396","https://openalex.org/W2157102033","https://openalex.org/W3096964161","https://openalex.org/W2131486661","https://openalex.org/W2005805562"],"abstract_inverted_index":{"Deep":[0],"learning":[1,28],"based":[2],"speech":[3,70],"enhancement":[4,31,59,87],"has":[5],"achieved":[6],"remarkable":[7],"success,":[8],"but":[9],"challenges":[10],"remain":[11],"in":[12,36,93],"low":[13],"signal-to-noise":[14],"ratio":[15],"(SNR)":[16],"nonstationary":[17],"noise":[18],"scenarios.":[19],"In":[20],"this":[21,82],"study,":[22],"we":[23],"propose":[24],"to":[25,65,67],"incorporate":[26],"diffusion-based":[27,43],"into":[29],"an":[30,62],"model":[32],"and":[33,48,84,96],"improve":[34],"robustness":[35],"extremely":[37],"noisy":[38,100],"conditions.":[39,101],"Specifically,":[40],"a":[41,56],"frequency-domain":[42],"generative":[44],"module":[45,60],"is":[46],"employed,":[47],"it":[49],"accepts":[50],"the":[51,75,79],"enhanced":[52],"signal":[53],"obtained":[54],"from":[55],"time-domain":[57],"supervised":[58],"as":[61],"auxiliary":[63],"input":[64],"learn":[66],"recover":[68],"clean":[69],"spectrograms.":[71],"Experimental":[72],"results":[73],"on":[74],"TIMIT":[76],"dataset":[77],"demonstrate":[78],"advantage":[80],"of":[81],"approach":[83],"show":[85],"better":[86],"performance":[88],"over":[89],"other":[90],"strong":[91],"baselines":[92],"both":[94],"-5":[95],"-10":[97],"dB":[98],"SNR":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}