{"id":"https://openalex.org/W4392904314","doi":"https://doi.org/10.1109/icassp48485.2024.10446719","title":"Dual-Path Minimum-Phase and All-Pass Decomposition Network for Single Channel Speech Dereverberation","display_name":"Dual-Path Minimum-Phase and All-Pass Decomposition Network for Single Channel Speech Dereverberation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904314","doi":"https://doi.org/10.1109/icassp48485.2024.10446719"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100731596","display_name":"Xi Liu","orcid":"https://orcid.org/0000-0002-4659-8955"},"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":true,"raw_author_name":"Xi Liu","raw_affiliation_strings":["The University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065795147","display_name":"Szu-Jui Chen","orcid":"https://orcid.org/0000-0002-6406-9280"},"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":"Szu-Jui Chen","raw_affiliation_strings":["The University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","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,Center for Robust Speech Systems (CRSS),TX,USA","Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100731596"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49523504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1261","last_page":"1265"},"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":0.9979000091552734,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7922261953353882},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6093387007713318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6076076626777649},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5389725565910339},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5145377516746521},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5106881260871887},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48894110321998596},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4818767011165619},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4720234274864197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44993072748184204},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.42858999967575073},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41901424527168274},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41646355390548706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4125884175300598},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.364422082901001},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.23074808716773987},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12658318877220154},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10487306118011475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922261953353882},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6093387007713318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6076076626777649},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5389725565910339},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5145377516746521},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5106881260871887},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48894110321998596},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4818767011165619},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4720234274864197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44993072748184204},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.42858999967575073},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41901424527168274},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41646355390548706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4125884175300598},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364422082901001},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23074808716773987},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12658318877220154},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10487306118011475},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":23,"referenced_works":["https://openalex.org/W1989314204","https://openalex.org/W2002938979","https://openalex.org/W2006129368","https://openalex.org/W2016449517","https://openalex.org/W2032857037","https://openalex.org/W2080811186","https://openalex.org/W2130722890","https://openalex.org/W2153418894","https://openalex.org/W2164502538","https://openalex.org/W2167583760","https://openalex.org/W2171049046","https://openalex.org/W2696967604","https://openalex.org/W2888867175","https://openalex.org/W2906724656","https://openalex.org/W2963941778","https://openalex.org/W2998161426","https://openalex.org/W3095913803","https://openalex.org/W3097777922","https://openalex.org/W4224925070","https://openalex.org/W4296069327","https://openalex.org/W6631362777","https://openalex.org/W6679043612","https://openalex.org/W6756168015"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W334008168","https://openalex.org/W2535773091"],"abstract_inverted_index":{"With":[0],"the":[1,21,104],"development":[2],"of":[3,65,91,109,120],"deep":[4,26],"neural":[5,55],"networks":[6],"(DNN),":[7],"many":[8],"DNN-based":[9],"speech":[10,72],"dereverberation":[11,28],"approaches":[12],"have":[13],"been":[14],"proposed":[15,110],"to":[16,58,88,102],"achieve":[17],"significant":[18],"improvement":[19],"over":[20],"traditional":[22],"methods.":[23,134],"However,":[24],"most":[25],"learning-based":[27],"methods":[29],"solely":[30],"focus":[31],"on":[32,114],"suppressing":[33],"time-frequency":[34],"domain":[35,40],"reverberations":[36,90],"without":[37],"utilizing":[38],"cepstral":[39,80],"features":[41],"which":[42],"are":[43],"potentially":[44],"useful":[45],"for":[46],"dereverberation.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,70,95],"propose":[52],"a":[53],"dual-path":[54],"network":[56],"structure":[57],"separately":[59],"process":[60],"minimum-phase":[61,75],"and":[62,76],"all-pass":[63,77],"components":[64,78,100],"single":[66],"channel":[67],"speech.":[68],"First,":[69],"decompose":[71],"signal":[73],"into":[74],"in":[79,118],"domain,":[81],"then":[82],"Conformer":[83],"embedded":[84],"U-Net":[85],"is":[86,112],"used":[87,122],"remove":[89],"both":[92],"components.":[93],"Finally,":[94],"combine":[96],"these":[97],"two":[98],"processed":[99],"together":[101],"synthesize":[103],"enhanced":[105],"output.":[106],"The":[107],"performance":[108],"method":[111,130],"tested":[113],"REVERB-Challenge":[115],"evaluation":[116],"dataset":[117],"terms":[119],"commonly":[121],"objective":[123],"metrics.":[124],"Experimental":[125],"results":[126],"demonstrate":[127],"that":[128],"our":[129],"outperforms":[131],"other":[132],"compared":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}