{"id":"https://openalex.org/W3134202725","doi":"https://doi.org/10.1109/iscslp49672.2021.9362064","title":"UNet++-Based Multi-Channel Speech Dereverberation and Distant Speech Recognition","display_name":"UNet++-Based Multi-Channel Speech Dereverberation and Distant Speech Recognition","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3134202725","doi":"https://doi.org/10.1109/iscslp49672.2021.9362064","mag":"3134202725"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101595500","display_name":"Tuo Zhao","orcid":"https://orcid.org/0000-0002-1536-7302"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuo Zhao","raw_affiliation_strings":["EECS Department, University of Missouri, Columbia, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033518479","display_name":"Yunxin Zhao","orcid":"https://orcid.org/0000-0001-5511-3692"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunxin Zhao","raw_affiliation_strings":["EECS Department, University of Missouri, Columbia, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["PAII, Inc., Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAII, Inc., Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059125065","display_name":"Mei Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei Han","raw_affiliation_strings":["PAII, Inc., Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAII, Inc., Palo Alto, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8129,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87368857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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":0.9939000010490417,"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/speech-recognition","display_name":"Speech recognition","score":0.7648552656173706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955475211143494},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6645651459693909},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5546852946281433},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5152740478515625},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4297955632209778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23534256219863892},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11021164059638977},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07249367237091064}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7648552656173706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955475211143494},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6645651459693909},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5546852946281433},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5152740478515625},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4297955632209778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23534256219863892},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11021164059638977},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07249367237091064},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1901129140","https://openalex.org/W2006129368","https://openalex.org/W2083751884","https://openalex.org/W2125114513","https://openalex.org/W2164502538","https://openalex.org/W2398972335","https://openalex.org/W2746457594","https://openalex.org/W2908510526","https://openalex.org/W2962780374","https://openalex.org/W2963197115","https://openalex.org/W2963250244","https://openalex.org/W2963941778","https://openalex.org/W2964089206","https://openalex.org/W2972389417","https://openalex.org/W2996290406","https://openalex.org/W6631362777","https://openalex.org/W6639824700","https://openalex.org/W6757817989","https://openalex.org/W6766380642"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W2106462793","https://openalex.org/W2963807216","https://openalex.org/W1628467322","https://openalex.org/W2264763718","https://openalex.org/W2143778427","https://openalex.org/W2889596223","https://openalex.org/W2160569100","https://openalex.org/W1589622339","https://openalex.org/W207491701"],"abstract_inverted_index":{"We":[0,71,87],"propose":[1,73],"a":[2,7,54,74],"novel":[3],"approach":[4],"of":[5,37,83,98,106,164],"using":[6],"newly":[8],"appeared":[9],"fully":[10],"convolutional":[11],"network":[12,44],"(FCN)":[13],"architecture,":[14],"UNet++,":[15],"for":[16,65,119],"multichannel":[17],"speech":[18,22,61],"dereverberation":[19,149],"and":[20,46,58,69,85,102,110,141,168],"distant":[21,94],"recognition":[23],"(DSR).":[24],"While":[25],"the":[26,59,92,104,121,145],"previous":[27],"FCN":[28],"architecture":[29],"UNet":[30,84,109,167],"is":[31],"good":[32],"at":[33],"utilizing":[34],"time-frequency":[35],"structures":[36],"speech,":[38],"UNet++":[39,51,107,137,165],"offers":[40],"better":[41],"robustness":[42],"in":[43,80],"depths":[45],"skip":[47],"connections.":[48],"For":[49],"DSR,":[50,120],"serves":[52],"as":[53],"feature":[55],"enhancement":[56],"front-end,":[57],"enhanced":[60],"features":[62],"are":[63,151,170],"used":[64],"acoustic":[66],"model":[67],"training":[68],"recognition.":[70],"also":[72,152,171],"frequency-dependent":[75],"convolution":[76],"scheme":[77],"(FDCS),":[78],"resulting":[79],"new":[81],"variants":[82],"UNet++.":[86],"present":[88],"DSR":[89],"results":[90,116,150],"from":[91,160],"multiple":[93],"microphone":[95],"(MDM)":[96],"datasets":[97],"AMI":[99],"meeting":[100],"corpus,":[101],"compare":[103],"performance":[105],"with":[108,138],"weighted":[111],"prediction":[112],"error":[113,127],"(WPE).":[114],"Our":[115],"demonstrate":[117],"that":[118],"UNet++-based":[122],"approaches":[123],"provide":[124],"large":[125,162],"word":[126],"rate":[128],"(WER)":[129],"reductions":[130],"over":[131,166],"its":[132],"UNetand":[133],"WPE-based":[134],"counterparts.":[135],"The":[136,148],"WPE":[139,169],"preprocessing":[140],"4-channel":[142],"input":[143],"achieves":[144],"lowest":[146],"WERs.":[147],"measured":[153],"by":[154],"speech-to-dereverberation":[155],"modulation":[156],"energy":[157],"ratio":[158],"(SRMR),":[159],"which":[161],"gains":[163],"observed.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}