{"id":"https://openalex.org/W3190227394","doi":"https://doi.org/10.1109/icassp43922.2022.9747795","title":"End-To-End Speech Recognition with Joint Dereverberation of Sub-Band Autoregressive Envelopes","display_name":"End-To-End Speech Recognition with Joint Dereverberation of Sub-Band Autoregressive Envelopes","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3190227394","doi":"https://doi.org/10.1109/icassp43922.2022.9747795","mag":"3190227394"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747795","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mpra.ub.uni-muenchen.de/75354/1/MPRA_paper_75354.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100786052","display_name":"Rohit Kumar","orcid":"https://orcid.org/0000-0001-5594-0129"},"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":"Rohit Kumar","raw_affiliation_strings":["Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","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":false,"raw_author_name":"Anurenjan Purushothaman","raw_affiliation_strings":["Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","College of Engineering, Thiruvanthapuram, India","Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"College of Engineering, Thiruvanthapuram, India","institution_ids":[]},{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050183512","display_name":"Anirudh Sreeram","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudh Sreeram","raw_affiliation_strings":["University of Southern California,Los Angels,USA","University of Southern California, Los Angels, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angels,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angels, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"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":["Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6057","last_page":"6061"},"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":0.9998999834060669,"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":0.9995999932289124,"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":0.8132623434066772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7126377820968628},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5620084404945374},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5523258447647095},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5312749147415161},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.521054208278656},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4540089964866638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4176233112812042},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4168863594532013},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4158782362937927},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4059056341648102},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34190964698791504},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2942064702510834},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10998839139938354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132623434066772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7126377820968628},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5620084404945374},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5523258447647095},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5312749147415161},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.521054208278656},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4540089964866638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4176233112812042},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4168863594532013},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4158782362937927},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4059056341648102},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34190964698791504},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2942064702510834},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10998839139938354},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747795","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai::75354","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/75354/1/MPRA_paper_75354.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"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"}],"best_oa_location":{"id":"pmh:oai::75354","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/75354/1/MPRA_paper_75354.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"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/W3190227394.pdf","grobid_xml":"https://content.openalex.org/works/W3190227394.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989314204","https://openalex.org/W2024490156","https://openalex.org/W2062164080","https://openalex.org/W2102113734","https://openalex.org/W2113932204","https://openalex.org/W2115055618","https://openalex.org/W2127141656","https://openalex.org/W2130722890","https://openalex.org/W2147166770","https://openalex.org/W2147299274","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2164502538","https://openalex.org/W2171928131","https://openalex.org/W2193413348","https://openalex.org/W2242685705","https://openalex.org/W2398042854","https://openalex.org/W2479014774","https://openalex.org/W2545177271","https://openalex.org/W2605195953","https://openalex.org/W2729190387","https://openalex.org/W2796485741","https://openalex.org/W2796868621","https://openalex.org/W2799800213","https://openalex.org/W2889166443","https://openalex.org/W2891952073","https://openalex.org/W2899771611","https://openalex.org/W2916024349","https://openalex.org/W2939777271","https://openalex.org/W2943554574","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2962832181","https://openalex.org/W2963040451","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2972818416","https://openalex.org/W2981022124","https://openalex.org/W3007328579","https://openalex.org/W3015870855","https://openalex.org/W3015966793","https://openalex.org/W3047835609","https://openalex.org/W3096073522","https://openalex.org/W3097056996","https://openalex.org/W3189281305","https://openalex.org/W3195593301","https://openalex.org/W4288366110","https://openalex.org/W4295274059","https://openalex.org/W6681922338","https://openalex.org/W6683968285","https://openalex.org/W6712626118","https://openalex.org/W6736155344","https://openalex.org/W6756040250","https://openalex.org/W6761806390"],"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/W2921005841"],"abstract_inverted_index":{"The":[0,45,59,76],"end-to-end":[1],"(E2E)":[2],"automatic":[3],"speech":[4,23,115,121],"recognition":[5,116,122],"(ASR)":[6],"systems":[7],"are":[8,24,48],"often":[9],"required":[10],"to":[11,148],"operate":[12],"in":[13,64],"reverberant":[14],"conditions,":[15],"where":[16],"the":[17,22,51,95,114,125,133,139,149,160,168],"long-term":[18],"sub-band":[19,42],"envelopes":[20,47],"of":[21,53,73,80,83,157],"temporally":[25],"smeared.":[26],"In":[27,136],"this":[28,65],"paper,":[29],"we":[30],"develop":[31],"a":[32,37,81],"feature":[33,98],"enhancement":[34,61,72],"approach":[35,143],"using":[36,50,103],"neural":[38,60,91],"model":[39,62,77],"operating":[40],"on":[41,124,132,159,167],"temporal":[43,46,74],"envelopes.":[44,75],"modeled":[49],"framework":[52],"frequency":[54],"domain":[55],"linear":[56],"prediction":[57],"(FDLP).":[58],"proposed":[63,140],"paper":[66],"performs":[67],"an":[68],"envelope":[69,96],"gain":[70],"based":[71,105],"architecture":[78],"consists":[79],"combination":[82],"convolutional":[84],"and":[85,100,164],"long":[86],"short":[87],"term":[88],"memory":[89],"(LSTM)":[90],"network":[92],"layers.":[93],"Further,":[94],"dereverberation,":[97],"extraction":[99],"acoustic":[101],"modeling":[102,142],"transformer":[104],"E2E":[106,120,151],"ASR":[107,152],"can":[108],"all":[109],"be":[110],"jointly":[111],"optimized":[112],"for":[113],"task.":[117],"We":[118],"perform":[119],"experiments":[123],"REVERB":[126,161],"challenge":[127,162],"dataset":[128,163],"as":[129,131],"well":[130],"VOiCES":[134,169],"dataset.":[135],"these":[137],"experiments,":[138],"joint":[141],"yields":[144],"significant":[145],"improvements":[146,156],"compared":[147],"baseline":[150],"system":[153],"(average":[154],"relative":[155],"21%":[158],"about":[165],"10%":[166],"dataset).":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}