{"id":"https://openalex.org/W4386951935","doi":"https://doi.org/10.1109/taslp.2023.3317570","title":"Speech Dereverberation With Frequency Domain Autoregressive Modeling","display_name":"Speech Dereverberation With Frequency Domain Autoregressive Modeling","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4386951935","doi":"https://doi.org/10.1109/taslp.2023.3317570"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3317570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3317570","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.13537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022033905","display_name":"Anurenjan Purushothaman","orcid":"https://orcid.org/0000-0001-6779-4122"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anurenjan Purushothaman","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0001-6779-4122","affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013284232","display_name":"Debottam Dutta","orcid":"https://orcid.org/0009-0009-6763-4511"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debottam Dutta","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0009-0009-6763-4511","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624406","display_name":"Rohit Kumar","orcid":"https://orcid.org/0000-0001-7067-1852"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Kumar","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0002-5779-9066","affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022033905"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":1.1514,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79139585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"29","last_page":"38"},"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":0.9987000226974487,"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":0.9979000091552734,"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/spectrogram","display_name":"Spectrogram","score":0.8316880464553833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045929670333862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7673258781433105},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6649664044380188},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5503248572349548},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.5030600428581238},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45356202125549316},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43447747826576233},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42603427171707153},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.41377994418144226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3470868170261383},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15306255221366882},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10877281427383423},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07574310898780823},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07494693994522095},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.07037085294723511},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06528159976005554}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8316880464553833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045929670333862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7673258781433105},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6649664044380188},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5503248572349548},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.5030600428581238},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45356202125549316},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43447747826576233},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42603427171707153},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.41377994418144226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3470868170261383},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15306255221366882},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10877281427383423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07574310898780823},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07494693994522095},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.07037085294723511},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06528159976005554},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2023.3317570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3317570","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":"pmh:oai:arXiv.org:2309.13537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13537","pdf_url":"https://arxiv.org/pdf/2309.13537","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.13537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13537","pdf_url":"https://arxiv.org/pdf/2309.13537","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5899999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386951935.pdf","grobid_xml":"https://content.openalex.org/works/W4386951935.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W13790222","https://openalex.org/W1897240248","https://openalex.org/W1973669708","https://openalex.org/W1989314204","https://openalex.org/W2035412504","https://openalex.org/W2044893557","https://openalex.org/W2053150333","https://openalex.org/W2062164080","https://openalex.org/W2077651652","https://openalex.org/W2101609516","https://openalex.org/W2108327698","https://openalex.org/W2113932204","https://openalex.org/W2115055618","https://openalex.org/W2119203697","https://openalex.org/W2125114513","https://openalex.org/W2128741405","https://openalex.org/W2131968171","https://openalex.org/W2144343635","https://openalex.org/W2144786298","https://openalex.org/W2147166770","https://openalex.org/W2147665979","https://openalex.org/W2148613904","https://openalex.org/W2152483743","https://openalex.org/W2156676906","https://openalex.org/W2158143227","https://openalex.org/W2164502538","https://openalex.org/W2242685705","https://openalex.org/W2296167893","https://openalex.org/W2395263859","https://openalex.org/W2488101143","https://openalex.org/W2609317876","https://openalex.org/W2729190387","https://openalex.org/W2755891984","https://openalex.org/W2760287881","https://openalex.org/W2796868621","https://openalex.org/W2890401420","https://openalex.org/W2899771611","https://openalex.org/W2939777271","https://openalex.org/W2943554574","https://openalex.org/W2962780374","https://openalex.org/W2962832181","https://openalex.org/W2962866211","https://openalex.org/W2963040451","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015199127","https://openalex.org/W3015395742","https://openalex.org/W3015870855","https://openalex.org/W3015966793","https://openalex.org/W3025515949","https://openalex.org/W3086154751","https://openalex.org/W3093664000","https://openalex.org/W3096073522","https://openalex.org/W3096408984","https://openalex.org/W3152963531","https://openalex.org/W3160085755","https://openalex.org/W3160207687","https://openalex.org/W3162308011","https://openalex.org/W3190227394","https://openalex.org/W3195593301","https://openalex.org/W4288366110","https://openalex.org/W4288558760","https://openalex.org/W4312219134","https://openalex.org/W4372263902","https://openalex.org/W6600546408","https://openalex.org/W6750150874","https://openalex.org/W6756040250","https://openalex.org/W6760112457","https://openalex.org/W6761806390","https://openalex.org/W6775498014"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Speech":[0],"applications":[1,36],"in":[2,35,76],"far-field":[3],"real":[4],"world":[5],"settings":[6],"often":[7],"deal":[8],"with":[9],"signals":[10,84,120,126],"that":[11,178],"are":[12,121,127],"corrupted":[13],"by":[14,66],"reverberation.":[15],"The":[16,71,117,135,220],"task":[17],"of":[18,47,62,80,140,150,182,214,234],"dereverberation":[19,49,139,184,210],"constitutes":[20],"an":[21,67],"important":[22],"step":[23],"to":[24,30,85,129],"improve":[25],"the":[26,32,52,56,60,77,81,87,111,124,131,147,151,155,161,165,173,179,187,196,217,231,235],"audible":[27],"quality":[28,54,222,233],"and":[29,55,89,114,123,142,186],"reduce":[31],"error":[33],"rates":[34],"like":[37],"automatic":[38],"speech":[39,48,53,83,183,221],"recognition":[40],"(ASR).":[41],"We":[42],"propose":[43],"a":[44],"unified":[45],"framework":[46],"for":[50,138,154,209],"improving":[51],"ASR":[57,158,162,189,198],"performance":[58,193],"using":[59,225],"approach":[61],"envelope-carrier":[63,119],"decomposition":[64],"provided":[65],"autoregressive":[68],"(AR)":[69],"model.":[70],"AR":[72],"model":[73,105,137,190],"is":[74,106],"applied":[75],"frequency":[78],"domain":[79],"sub-band":[82,112,125],"separate":[86],"envelope":[88,113,141],"carrier":[90,115,143],"parts.":[91],"A":[92],"novel":[93],"neural":[94],"architecture":[95],"based":[96],"on":[97,164,172,201],"dual":[98],"path":[99],"long":[100],"short":[101],"term":[102],"memory":[103],"(DPLSTM)":[104],"proposed,":[107],"which":[108],"jointly":[109],"enhances":[110],"components.":[116],"dereverberated":[118],"modulated":[122],"synthesized":[128],"reconstruct":[130],"audio":[132],"signal":[133],"back.":[134],"DPLSTM":[136],"components":[144],"also":[145],"allows":[146],"joint":[148,180],"learning":[149,181],"network":[152,185],"weights":[153],"down":[156],"stream":[157],"task.":[159],"In":[160],"tasks":[163],"REVERB":[166],"challenge":[167],"dataset":[168],"as":[169,171,204,206],"well":[170,205],"VOiCES":[174],"dataset,":[175],"we":[176],"illustrate":[177],"E2E":[188],"yields":[191],"significant":[192],"improvements":[194,213],"over":[195,216],"baseline":[197,218],"system":[199],"trained":[200],"log-mel":[202],"spectrogram":[203],"other":[207],"benchmarks":[208],"(average":[211],"relative":[212],"10-24%":[215],"system).":[219],"improvements,":[223],"evaluated":[224],"subjective":[226],"listening":[227],"tests,":[228],"further":[229],"highlight":[230],"improved":[232],"reconstructed":[236],"audio.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-09-23T00:00:00"}