{"id":"https://openalex.org/W4375869450","doi":"https://doi.org/10.1109/icassp49357.2023.10095906","title":"Convolutional Recurrent MetriCGAN With Spectral Dimension Compression For Full-Band Speech Enhancement","display_name":"Convolutional Recurrent MetriCGAN With Spectral Dimension Compression For Full-Band Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869450","doi":"https://doi.org/10.1109/icassp49357.2023.10095906"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095906","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/A5038001536","display_name":"Zhongshu Hou","orcid":"https://orcid.org/0009-0000-5589-5372"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongshu Hou","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]},{"raw_affiliation_string":"Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","institution_ids":[]},{"raw_affiliation_string":"Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046157506","display_name":"Qinwen Hu","orcid":"https://orcid.org/0000-0003-0087-7200"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinwen Hu","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]},{"raw_affiliation_string":"Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","institution_ids":[]},{"raw_affiliation_string":"Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101737173","display_name":"Tianchi Sun","orcid":"https://orcid.org/0000-0002-4589-7769"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]},{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianchi Sun","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China","Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]},{"raw_affiliation_string":"Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103226450","display_name":"Yuxiang Hu","orcid":"https://orcid.org/0009-0005-8536-3840"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Hu","raw_affiliation_strings":["NJU-Horizon Intelligent Audio Lab,Horizon Robotics,Beijing,China,100094","Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"NJU-Horizon Intelligent Audio Lab,Horizon Robotics,Beijing,China,100094","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030243018","display_name":"Changbao Zhu","orcid":"https://orcid.org/0000-0002-4438-8102"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbao Zhu","raw_affiliation_strings":["NJU-Horizon Intelligent Audio Lab,Horizon Robotics,Beijing,China,100094","Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"NJU-Horizon Intelligent Audio Lab,Horizon Robotics,Beijing,China,100094","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437946","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-0164-1112"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China","Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]},{"raw_affiliation_string":"Horizon Robotics, NJU-Horizon Intelligent Audio Lab, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038001536"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4401726824","https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.8151,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70347418,"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":"2"},"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":0.9969000220298767,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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":0.7550495862960815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7006668448448181},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6640588045120239},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6235765814781189},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5136091709136963},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.4985463619232178},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.48353123664855957},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.44590768218040466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3833017349243164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32137244939804077},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.24574995040893555},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2201816439628601},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.11892181634902954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09345817565917969},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07548806071281433},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06894281506538391}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7550495862960815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7006668448448181},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6640588045120239},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6235765814781189},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5136091709136963},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.4985463619232178},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.48353123664855957},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.44590768218040466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3833017349243164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32137244939804077},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.24574995040893555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2201816439628601},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.11892181634902954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09345817565917969},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07548806071281433},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06894281506538391},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095906","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2949558265","https://openalex.org/W3120336970","https://openalex.org/W4221143458","https://openalex.org/W4225302959","https://openalex.org/W4321453038","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W2610189143","https://openalex.org/W2159424856","https://openalex.org/W4390516098","https://openalex.org/W2136831313","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2132373020","https://openalex.org/W2096049278","https://openalex.org/W3211091508","https://openalex.org/W68492818"],"abstract_inverted_index":{"MetricGAN":[0],"and":[1,78],"its":[2],"variations":[3],"have":[4],"been":[5],"proven":[6],"to":[7,21,54],"be":[8],"an":[9],"effective":[10],"wide-band":[11],"speech":[12],"enhancement":[13,23],"model.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18],"expand":[19],"it":[20,69],"full-band":[22],"by":[24],"combining":[25],"our":[26],"recently":[27],"proposed":[28,50],"learnable":[29],"spectral":[30],"dimension":[31],"compression":[32],"mapping":[33],"strategy.":[34],"The":[35,49],"encoder-decoder":[36],"structure":[37],"with":[38],"a":[39,71],"time-frequency":[40],"convolutional":[41],"recurrent":[42],"network":[43],"is":[44,52],"utilized":[45],"as":[46],"the":[47,55,66],"generator.":[48],"model":[51],"submitted":[53],"ICASSP":[56],"Signal":[57],"Processing":[58],"Grand":[59],"Challenge:":[60],"DNS-5":[61],"Challenge":[62],"(2023).":[63],"Without":[64],"using":[65],"enrollment":[67],"speech,":[68],"obtains":[70],"final":[72],"score":[73],"of":[74],"0.548":[75],"on":[76,80],"Track-1":[77],"0.559":[79],"Track-2.":[81]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
