{"id":"https://openalex.org/W4308168108","doi":"https://doi.org/10.48550/arxiv.2211.01189","title":"Inference and Denoise: Causal Inference-based Neural Speech Enhancement","display_name":"Inference and Denoise: Causal Inference-based Neural Speech Enhancement","publication_year":2022,"publication_date":"2022-11-02","ids":{"openalex":"https://openalex.org/W4308168108","doi":"https://doi.org/10.48550/arxiv.2211.01189"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.01189","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.01189","pdf_url":"https://arxiv.org/pdf/2211.01189","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.01189","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060785253","display_name":"Tsun-An Hsieh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hsieh, Tsun-An","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chao-Han Huck","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Pin-Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siniscalchi, Sabato Marco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsao, Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060785253"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9767000079154968,"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/inference","display_name":"Inference","score":0.7370625734329224},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6956405639648438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6379042267799377},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.6351475119590759},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.533980131149292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5173532366752625},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5153514742851257},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.423404723405838},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42141905426979065},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41030949354171753},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4059985280036926},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2631341218948364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19112297892570496},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09074369072914124},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07612165808677673}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7370625734329224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6956405639648438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6379042267799377},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.6351475119590759},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.533980131149292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5173532366752625},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5153514742851257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.423404723405838},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42141905426979065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41030949354171753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4059985280036926},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2631341218948364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19112297892570496},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09074369072914124},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07612165808677673},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.01189","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.01189","pdf_url":"https://arxiv.org/pdf/2211.01189","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.01189","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.01189","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.01189","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.01189","pdf_url":"https://arxiv.org/pdf/2211.01189","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2978999882","https://openalex.org/W3141031773","https://openalex.org/W1595686156","https://openalex.org/W2181392282","https://openalex.org/W2119369480","https://openalex.org/W2744070736","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,9,15,23,27,67,79,83,88,91,108,124],"speech":[4,31,43],"enhancement":[5,32,57,84],"(SE)":[6],"task":[7],"within":[8],"causal":[10,29,109],"inference":[11],"paradigm":[12],"by":[13],"modeling":[14],"noise":[16,46,70,80,94],"presence":[17,68,92],"as":[18,71],"an":[19,40],"intervention.":[20],"Based":[21],"on":[22],"potential":[24],"outcome":[25],"framework,":[26],"proposed":[28],"inference-based":[30],"(CISE)":[33],"separates":[34],"clean":[35],"and":[36,48,78,127,131],"noisy":[37,42],"frames":[38,53],"in":[39,123],"intervened":[41],"using":[44],"a":[45,101,118],"detector":[47,81],"assigns":[49],"both":[50],"sets":[51],"of":[52,69,90,93],"to":[54,60,87,106],"two":[55],"mask-based":[56,120],"modules":[58],"(EMs)":[59],"perform":[61],"noise-conditional":[62],"SE.":[63],"Specifically,":[64],"we":[65,99],"use":[66],"guidance":[72],"for":[73,95],"EM":[74],"selection":[75],"during":[76],"training,":[77],"selects":[82],"module":[85],"according":[86],"prediction":[89],"each":[96],"frame.":[97],"Moreover,":[98],"derived":[100],"SE-specific":[102],"average":[103],"treatment":[104],"effect":[105,110],"quantify":[107],"adequately.":[111],"Experimental":[112],"evidence":[113],"demonstrates":[114],"that":[115],"CISE":[116],"outperforms":[117],"non-causal":[119],"SE":[121,136],"approach":[122],"studied":[125],"settings":[126],"has":[128],"better":[129],"performance":[130],"efficiency":[132],"than":[133],"more":[134],"complex":[135],"models.":[137]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}