{"id":"https://openalex.org/W3212500403","doi":"https://doi.org/10.1109/mlsp52302.2021.9596103","title":"Optimizing Time Domain Fully Convolutional Networks for 3D Speech Enhancement in a Reverberant Environment Using Perceptual Losses","display_name":"Optimizing Time Domain Fully Convolutional Networks for 3D Speech Enhancement in a Reverberant Environment Using Perceptual Losses","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3212500403","doi":"https://doi.org/10.1109/mlsp52302.2021.9596103","mag":"3212500403"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5059048857","display_name":"Heitor R. Guimar\u00e3es","orcid":"https://orcid.org/0000-0001-9929-9871"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Heitor R. Guimaraes","raw_affiliation_strings":["Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","Itati Unibanco, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]},{"raw_affiliation_string":"Itati Unibanco, S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024992483","display_name":"Wesley Beccaro","orcid":"https://orcid.org/0000-0001-6599-2344"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wesley Beccaro","raw_affiliation_strings":["Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021252790","display_name":"Miguel Arjona Ram\u00edrez","orcid":"https://orcid.org/0000-0002-7107-0888"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Miguel A. Ramirez","raw_affiliation_strings":["Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059048857"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":0.6094,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67782285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7788561582565308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6915662884712219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6045236587524414},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.5504317879676819},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49503034353256226},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.46294912695884705},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44764021039009094},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41368138790130615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36853861808776855},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.261339396238327},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15865734219551086},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1490362584590912}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7788561582565308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915662884712219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6045236587524414},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.5504317879676819},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49503034353256226},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46294912695884705},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44764021039009094},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41368138790130615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36853861808776855},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.261339396238327},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15865734219551086},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1490362584590912},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G828258283","display_name":null,"funder_award_id":"2018/26455-8,2019/07665-4","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2405774341","https://openalex.org/W2790372648","https://openalex.org/W2902132730","https://openalex.org/W2914048585","https://openalex.org/W2949756029","https://openalex.org/W2963045393","https://openalex.org/W2963453742","https://openalex.org/W2973049979","https://openalex.org/W2998445964","https://openalex.org/W3004309045","https://openalex.org/W3008487564","https://openalex.org/W3026815601","https://openalex.org/W3115341864","https://openalex.org/W3141443761","https://openalex.org/W3158243217","https://openalex.org/W3167533889","https://openalex.org/W3197284240","https://openalex.org/W3197912330","https://openalex.org/W3212486120","https://openalex.org/W4253928870","https://openalex.org/W4289242435","https://openalex.org/W6756251360","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W3043214604","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2401089611"],"abstract_inverted_index":{"Noise":[0],"in":[1,24,100,128],"3D":[2,20],"reverberant":[3],"environment":[4],"is":[5],"detrimental":[6],"to":[7,19,93],"several":[8],"downstream":[9],"applications.":[10],"In":[11],"this":[12,123],"work,":[13],"we":[14],"propose":[15],"a":[16,37,46,57,83,96],"novel":[17],"approach":[18],"speech":[21],"enhancement":[22],"directly":[23],"the":[25,29,43,53,61,77,101,105,116,132],"time":[26],"domain":[27],"through":[28],"usage":[30],"of":[31,45,52,60,76,86,98,131],"Fully":[32],"Convolutional":[33],"Networks":[34],"(FCN)":[35],"with":[36],"custom":[38],"loss":[39],"function":[40],"based":[41,72,107,121],"on":[42,50,73,108,122],"combination":[44,112],"perceptual":[47],"loss,":[48],"built":[49],"top":[51],"wav2vec":[54],"model":[55,81],"and":[56,69,95,110],"soft":[58],"version":[59],"short-time":[62],"objective":[63],"intelligibility":[64],"(STOI)":[65],"metric.":[66],"The":[67],"dataset":[68],"experiments":[70],"were":[71],"Task":[74,129],"1":[75,130],"L3DAS21":[78,133],"challenge.":[79,134],"Our":[80,119],"achieves":[82],"STOI":[84,109],"score":[85,97],"0.82,":[87],"word":[88],"error":[89],"rate":[90],"(WER)":[91],"equal":[92],"0.36,":[94],"0.73":[99],"metric":[102],"proposed":[103],"by":[104],"challenge":[106],"WER":[111],"using":[113],"as":[114],"reference":[115],"development":[117],"set.":[118],"submission,":[120],"method,":[124],"was":[125],"ranked":[126],"second":[127]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}