{"id":"https://openalex.org/W4375869009","doi":"https://doi.org/10.1109/icassp49357.2023.10095657","title":"Two-Stage UNet with Multi-Axis Gated Multilayer Perceptron for Monaural Noisy-Reverberant Speech Enhancement","display_name":"Two-Stage UNet with Multi-Axis Gated Multilayer Perceptron for Monaural Noisy-Reverberant Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869009","doi":"https://doi.org/10.1109/icassp49357.2023.10095657"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5090668921","display_name":"Zehua Zhang","orcid":"https://orcid.org/0000-0003-3215-5317"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zehua Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101885098","display_name":"Shiyun Xu","orcid":"https://orcid.org/0000-0002-3278-5151"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyun Xu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044255594","display_name":"Xuyi Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyi Zhuang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041945581","display_name":"Lianyu Zhou","orcid":"https://orcid.org/0000-0001-8212-0839"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianyu Zhou","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084369581","display_name":"Heng Li","orcid":"https://orcid.org/0000-0003-1734-0530"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Li","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651653","display_name":"Mingjiang Wang","orcid":"https://orcid.org/0000-0002-4706-009X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjiang Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090668921"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.8151,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7027856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9973000288009644,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9972000122070312,"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/monaural","display_name":"Monaural","score":0.8230053186416626},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7923597693443298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7587378025054932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7247110605239868},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5852807760238647},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.572702944278717},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5093927979469299},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.49297070503234863},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4923187494277954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4779950678348541},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47060427069664},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46874454617500305},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.4653642177581787},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4621911644935608},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.26430195569992065},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15335547924041748},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10994565486907959},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07591217756271362}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8230053186416626},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7923597693443298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587378025054932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7247110605239868},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5852807760238647},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.572702944278717},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5093927979469299},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.49297070503234863},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4923187494277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4779950678348541},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47060427069664},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46874454617500305},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4653642177581787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4621911644935608},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26430195569992065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15335547924041748},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10994565486907959},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07591217756271362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1998648683","https://openalex.org/W2006129368","https://openalex.org/W2125114513","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2952218014","https://openalex.org/W2991361823","https://openalex.org/W3096408984","https://openalex.org/W3097034112","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3109394096","https://openalex.org/W3160085755","https://openalex.org/W3162493033","https://openalex.org/W3198680319","https://openalex.org/W3213188934","https://openalex.org/W3215881519","https://openalex.org/W4221149546","https://openalex.org/W4224934178","https://openalex.org/W4225302959","https://openalex.org/W4297841575","https://openalex.org/W4312678820","https://openalex.org/W6796417832"],"related_works":["https://openalex.org/W2621851636","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2076543106","https://openalex.org/W2523437662","https://openalex.org/W89844371","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W4387048144"],"abstract_inverted_index":{"In":[0],"denoising":[1],"and":[2,12,19,35,49],"de-reverberation":[3],"tasks,":[4],"the":[5,63,76,81,102],"dominant":[6],"methods":[7],"are":[8],"complex":[9,13,32,36],"spectral":[10,14,33,37],"masking":[11,34],"mapping.":[15,38],"To":[16],"combine":[17],"advantages":[18],"improve":[20],"speech":[21,58,73,108],"enhancement":[22],"performance,":[23],"we":[24,61],"propose":[25],"a":[26,41,90],"two-stage":[27],"UNet":[28],"(TSUNet)":[29],"to":[30,46,68],"estimate":[31],"We":[39],"use":[40,62],"multi-axis":[42],"gated":[43],"multilayer":[44],"perceptron":[45],"build":[47],"global":[48],"local":[50],"attention":[51,66],"modules":[52],"of":[53,80],"linear":[54],"complexity":[55],"for":[56],"extracting":[57],"features.":[59,74],"Furthermore,":[60],"residual":[64],"channel":[65],"block":[67],"further":[69],"filter":[70],"out":[71],"important":[72],"On":[75],"blind":[77],"test":[78],"dataset":[79],"Deep":[82],"Noise":[83],"Suppression":[84],"Challenge,":[85],"our":[86],"proposed":[87],"TSUNet":[88,97],"has":[89],"massive":[91],"advantage":[92],"over":[93],"other":[94],"state-of-the-art":[95],"models.":[96],"performs":[98],"significantly":[99],"better":[100],"than":[101],"most":[103],"recent":[104],"models":[105],"at":[106],"noisy-reverberant":[107],"enhancement.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}