{"id":"https://openalex.org/W3165776651","doi":"https://doi.org/10.1109/taslp.2022.3161143","title":"Self-Attending RNN for Speech Enhancement to Improve Cross-Corpus Generalization","display_name":"Self-Attending RNN for Speech Enhancement to Improve Cross-Corpus Generalization","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3165776651","doi":"https://doi.org/10.1109/taslp.2022.3161143","mag":"3165776651","pmid":"https://pubmed.ncbi.nlm.nih.gov/36245814"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3161143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3161143","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.12831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"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":"Ashutosh Pandey","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-3352-7453","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 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":["Department of Computer Science and Engineering, and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, 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":7.3528,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.98071164,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1374","last_page":"1385"},"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":0.9997000098228455,"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":0.9994000196456909,"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/generalization","display_name":"Generalization","score":0.7131733894348145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5046626329421997},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4914447069168091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4843541383743286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36355265974998474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628872036933899},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.36199885606765747},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.330428808927536},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.22772634029388428},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1305268108844757},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10018602013587952}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7131733894348145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5046626329421997},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4914447069168091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4843541383743286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36355265974998474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628872036933899},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36199885606765747},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.330428808927536},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.22772634029388428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1305268108844757},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10018602013587952},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2022.3161143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3161143","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:36245814","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36245814","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":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:arXiv.org:2105.12831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12831","pdf_url":"https://arxiv.org/pdf/2105.12831","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9560045","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9560045","pdf_url":null,"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":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.12831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12831","pdf_url":"https://arxiv.org/pdf/2105.12831","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"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/G3481055361","display_name":null,"funder_award_id":"R01 DC015521","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G404307092","display_name":null,"funder_award_id":"R02DC015521","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G4332130492","display_name":null,"funder_award_id":"R01DC012048","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1974387177","https://openalex.org/W2024490156","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2095705004","https://openalex.org/W2141998673","https://openalex.org/W2165899180","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2405774341","https://openalex.org/W2462831000","https://openalex.org/W2516342150","https://openalex.org/W2603567530","https://openalex.org/W2678916739","https://openalex.org/W2747161606","https://openalex.org/W2774389566","https://openalex.org/W2798405286","https://openalex.org/W2802304149","https://openalex.org/W2804078698","https://openalex.org/W2889286744","https://openalex.org/W2891355459","https://openalex.org/W2892009249","https://openalex.org/W2892356933","https://openalex.org/W2899663614","https://openalex.org/W2899771611","https://openalex.org/W2902132730","https://openalex.org/W2937484199","https://openalex.org/W2938901746","https://openalex.org/W2943554574","https://openalex.org/W2943895317","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963103134","https://openalex.org/W2963112338","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963453742","https://openalex.org/W2963828919","https://openalex.org/W2964121744","https://openalex.org/W2972443522","https://openalex.org/W2991324852","https://openalex.org/W2991361823","https://openalex.org/W2998678989","https://openalex.org/W2998832642","https://openalex.org/W3002439978","https://openalex.org/W3015197852","https://openalex.org/W3015199127","https://openalex.org/W3015219411","https://openalex.org/W3016129867","https://openalex.org/W3017350693","https://openalex.org/W3026111682","https://openalex.org/W3049430014","https://openalex.org/W3094199623","https://openalex.org/W3094911989","https://openalex.org/W3095820034","https://openalex.org/W3096159803","https://openalex.org/W3096408984","https://openalex.org/W3097627357","https://openalex.org/W3097945073","https://openalex.org/W3102190437","https://openalex.org/W3134695619","https://openalex.org/W3156857934","https://openalex.org/W3161480375","https://openalex.org/W3162698503","https://openalex.org/W3163464523","https://openalex.org/W3164605550","https://openalex.org/W3197042120","https://openalex.org/W3197912330","https://openalex.org/W4231807801","https://openalex.org/W4253928870","https://openalex.org/W4289242435","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6739901393","https://openalex.org/W6745245109","https://openalex.org/W6752378368","https://openalex.org/W6755977528","https://openalex.org/W6756251360","https://openalex.org/W6757632829","https://openalex.org/W6762114000","https://openalex.org/W6770514768","https://openalex.org/W6772622344","https://openalex.org/W6780226713","https://openalex.org/W6783890765","https://openalex.org/W6793619966"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"Deep":[0],"neural":[1,72,87],"networks":[2,88],"(DNNs)":[3],"represent":[4],"the":[5,136,166],"mainstream":[6],"methodology":[7],"for":[8,61,75,152,173],"supervised":[9],"speech":[10,56,77,121,141],"enhancement,":[11,122,148],"primarily":[12],"due":[13],"to":[14,17,37,39,79,119,140],"their":[15],"capability":[16],"model":[18],"complex":[19,143],"functions":[20],"using":[21],"hierarchical":[22],"representations.":[23],"However,":[24],"a":[25,33,50,69,162],"recent":[26],"study":[27,172],"revealed":[28],"that":[29,113,135],"DNNs":[30],"trained":[31],"on":[32,100],"single":[34],"corpus":[35,54],"fail":[36],"generalize":[38],"untrained":[40],"corpora,":[41],"especially":[42],"in":[43,106,170],"low":[44,107],"signal-to-noise":[45],"ratio":[46],"(SNR)":[47],"conditions.":[48,109],"Developing":[49],"noise,":[51],"speaker,":[52],"and":[53,94,126,146,154,177],"independent":[55],"enhancement":[57,78],"algorithm":[58],"is":[59],"essential":[60],"real-world":[62],"applications.":[63],"In":[64],"this":[65,171],"study,":[66],"we":[67,130],"propose":[68],"self-attending":[70],"recurrent":[71,86],"network":[73],"(SARNN)":[74],"time-domain":[76,120,147],"improve":[80],"cross-corpus":[81],"generalization.":[82],"SARNN":[83,99,114,155],"comprises":[84],"of":[85,165],"(RNNs)":[89],"augmented":[90],"with":[91,103,156],"self-attention":[92],"blocks":[93],"feedforward":[95],"blocks.":[96],"We":[97,159],"evaluate":[98],"different":[101],"corpora":[102],"nonstationary":[104],"noises":[105],"SNR":[108],"Experimental":[110],"results":[111,151],"demonstrate":[112],"substantially":[115],"outperforms":[116],"competitive":[117],"approaches":[118,139],"such":[123],"as":[124],"RNNs":[125],"dual-path":[127],"SARNNs.":[128],"Additionally,":[129],"report":[131],"an":[132],"important":[133],"finding":[134],"two":[137],"popular":[138],"enhancement:":[142],"spectral":[144],"mapping":[145],"obtain":[149],"similar":[150],"RNN":[153],"large-scale":[157],"training.":[158],"also":[160],"provide":[161],"challenging":[163],"subset":[164],"test":[167],"set":[168],"used":[169],"evaluating":[174],"future":[175],"algorithms":[176],"facilitating":[178],"direct":[179],"comparisons.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}