{"id":"https://openalex.org/W3042853995","doi":"https://doi.org/10.21437/interspeech.2020-2048","title":"SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation Using Optimally Smoothed Spectral Mapping","display_name":"SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation Using Optimally Smoothed Spectral Mapping","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3042853995","doi":"https://doi.org/10.21437/interspeech.2020-2048","mag":"3042853995"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2048","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2007.09131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047630225","display_name":"Vinay Kothapally","orcid":"https://orcid.org/0000-0002-2111-3333"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinay Kothapally","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101861591","display_name":"Wei Xia","orcid":"https://orcid.org/0009-0009-4734-6256"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075220607","display_name":"Shahram Ghorbani","orcid":"https://orcid.org/0000-0002-8118-5515"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahram Ghorbani","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652844","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-4942-7748"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100632700","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0002-3294-5725"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["Stanford University, Stanford, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3935","last_page":"3939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.8351086974143982},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6753532290458679},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6265654563903809},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5871651768684387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5863257646560669},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5395940542221069},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.528312623500824},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.51186603307724},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44618386030197144},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4225158095359802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3757930397987366},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.28177350759506226},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08130934834480286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351086974143982},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6753532290458679},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6265654563903809},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5871651768684387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5863257646560669},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5395940542221069},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.528312623500824},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.51186603307724},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44618386030197144},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4225158095359802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3757930397987366},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.28177350759506226},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08130934834480286},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2048","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"mag:3042853995","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.09131","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-125442","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-125442","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.2007.09131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.09131","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"mag:3042853995","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.09131","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[{"score":0.6899999976158142,"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":25,"referenced_works":["https://openalex.org/W1512562331","https://openalex.org/W1901129140","https://openalex.org/W1983812858","https://openalex.org/W1989314204","https://openalex.org/W2097117768","https://openalex.org/W2130722890","https://openalex.org/W2147166770","https://openalex.org/W2148613904","https://openalex.org/W2158336491","https://openalex.org/W2164502538","https://openalex.org/W2188162373","https://openalex.org/W2194775991","https://openalex.org/W2242685705","https://openalex.org/W2395263859","https://openalex.org/W2463481471","https://openalex.org/W2726515241","https://openalex.org/W2762693443","https://openalex.org/W2808631503","https://openalex.org/W2884436604","https://openalex.org/W2890964092","https://openalex.org/W2928133111","https://openalex.org/W2940275453","https://openalex.org/W2943554574","https://openalex.org/W2963446712","https://openalex.org/W2963941778"],"related_works":["https://openalex.org/W3095913803","https://openalex.org/W2791833049","https://openalex.org/W3199713199","https://openalex.org/W2764005420","https://openalex.org/W3202709306","https://openalex.org/W3088159194","https://openalex.org/W3031135612","https://openalex.org/W3105224243","https://openalex.org/W2963954250","https://openalex.org/W3162629387","https://openalex.org/W2775477443","https://openalex.org/W3168770049","https://openalex.org/W2810843531","https://openalex.org/W3091830790","https://openalex.org/W3017216675","https://openalex.org/W2965016789","https://openalex.org/W3045376303","https://openalex.org/W3129640789","https://openalex.org/W2996342087","https://openalex.org/W2797972631"],"abstract_inverted_index":{"The":[0],"reliability":[1],"of":[2,20,25,71,79,82,98,116,140],"using":[3],"fully":[4],"convolutional":[5,53],"networks":[6],"(FCNs)":[7],"has":[8],"been":[9],"successfully":[10],"demonstrated":[11],"by":[12],"recent":[13],"studies":[14],"in":[15,130],"many":[16],"speech":[17,131,142,146],"applications.":[18],"One":[19],"the":[21,29,68,72,77,96,99,108,114,121,138,160],"most":[22],"popular":[23],"variants":[24],"these":[26],"FCNs":[27],"is":[28,32],"`U-Net',":[30],"which":[31,91],"an":[33],"encoder-decoder":[34],"network":[35],"with":[36,51,58],"skip":[37,49],"connections.":[38],"In":[39],"this":[40],"study,":[41],"we":[42,46,106],"propose":[43,76],"`SkipConvNet'":[44],"where":[45],"replace":[47],"each":[48],"connection":[50],"multiple":[52],"modules":[54],"to":[55,66,93,112,136],"provide":[56],"decoder":[57],"intuitive":[59],"feature":[60],"maps":[61],"rather":[62],"than":[63],"encoder's":[64],"output":[65],"improve":[67],"learning":[69],"capacity":[70],"network.":[73,100],"We":[74,124],"also":[75],"use":[78,107],"optimal":[80],"smoothing":[81],"power":[83],"spectral":[84],"density":[85],"(PSD)":[86],"as":[87,145],"a":[88],"pre-processing":[89],"step,":[90],"helps":[92],"further":[94],"enhance":[95],"efficiency":[97,139],"To":[101],"evaluate":[102],"our":[103],"proposed":[104,161],"system,":[105],"REVERB":[109],"challenge":[110],"corpus":[111],"assess":[113],"performance":[115],"various":[117],"enhancement":[118],"approaches":[119],"under":[120],"same":[122],"conditions.":[123],"focus":[125],"solely":[126],"on":[127,152],"monitoring":[128],"improvements":[129],"quality":[132],"and":[133,148],"their":[134],"contribution":[135],"improving":[137],"back-end":[141],"systems,":[143],"such":[144],"recognition":[147],"speaker":[149],"verification,":[150],"trained":[151],"only":[153],"clean":[154],"speech.":[155],"Experimental":[156],"findings":[157],"show":[158],"that":[159],"system":[162],"consistently":[163],"outperforms":[164],"other":[165],"approaches.":[166]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}