{"id":"https://openalex.org/W3080282677","doi":"https://doi.org/10.1145/3404555.3404618","title":"Amplitude Consistent Enhancement for Speech Dereverberation","display_name":"Amplitude Consistent Enhancement for Speech Dereverberation","publication_year":2020,"publication_date":"2020-04-23","ids":{"openalex":"https://openalex.org/W3080282677","doi":"https://doi.org/10.1145/3404555.3404618","mag":"3080282677"},"language":"en","primary_location":{"id":"doi:10.1145/3404555.3404618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404555.3404618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","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/A5100719425","display_name":"Chunlei Liu","orcid":"https://orcid.org/0000-0002-7364-7900"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunlei Liu","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100719425"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09242923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"412","last_page":"417"},"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":0.9972000122070312,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.8944798707962036},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7471054792404175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7049379348754883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6718297600746155},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.6547733545303345},{"id":"https://openalex.org/keywords/superposition-principle","display_name":"Superposition principle","score":0.5967269539833069},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5136127471923828},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.43044543266296387},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41765788197517395},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4123036861419678},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3831852078437805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32061147689819336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18395695090293884},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12095406651496887}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8944798707962036},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7471054792404175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049379348754883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6718297600746155},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.6547733545303345},{"id":"https://openalex.org/C27753989","wikidata":"https://www.wikidata.org/wiki/Q284885","display_name":"Superposition principle","level":2,"score":0.5967269539833069},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5136127471923828},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.43044543266296387},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41765788197517395},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4123036861419678},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3831852078437805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32061147689819336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18395695090293884},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12095406651496887},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404555.3404618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404555.3404618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1897240248","https://openalex.org/W2006129368","https://openalex.org/W2010275911","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2120847449","https://openalex.org/W2144404214","https://openalex.org/W2144786298","https://openalex.org/W2242685705","https://openalex.org/W2291877678","https://openalex.org/W2379331960","https://openalex.org/W2609317876","https://openalex.org/W2746904187","https://openalex.org/W2889286744","https://openalex.org/W2890820256","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W6681386091"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2157977645","https://openalex.org/W2546593254","https://openalex.org/W1980687383"],"abstract_inverted_index":{"The":[0,33,128],"mapping":[1],"and":[2,36,104,141,145],"masking":[3],"methods":[4,12],"based":[5],"on":[6],"deep":[7,91],"learning":[8],"are":[9,39],"both":[10],"essential":[11],"for":[13],"speech":[14,26,63,106,129],"dereverberation":[15,130],"at":[16],"present,":[17],"which":[18],"typically":[19],"enhance":[20],"the":[21,24,29,43,48,56,60,68,90,97,102,108,123,134,139,149],"amplitude":[22,38,77],"of":[23,101,116,126],"reverberant":[25,30,34],"while":[27],"letting":[28],"phase":[31,35],"unprocessed.":[32],"enhanced":[37],"used":[40],"to":[41,82,88,121],"synthesize":[42],"target":[44],"speech.":[45],"However,":[46],"because":[47],"overlapping":[49],"frames":[50],"interfere":[51],"with":[52,148],"each":[53],"other":[54],"during":[55],"superposition":[57],"process":[58],"(overlap-and-add),":[59],"final":[61],"synthesized":[62,103],"signal":[64,151],"will":[65],"deviate":[66],"from":[67],"ideal":[69],"value.":[70],"In":[71],"this":[72,84],"paper,":[73],"we":[74,95,112],"propose":[75,113],"an":[76,118],"consistent":[78],"enhancement":[79],"method":[80,115,136],"(ACE)":[81],"solve":[83],"problem.":[85],"With":[86],"ACE":[87],"train":[89],"neural":[92],"networks":[93],"(DNNs),":[94],"use":[96],"difference":[98],"between":[99],"amplitudes":[100],"clean":[105],"as":[107],"loss":[109],"function.":[110],"Also,":[111],"a":[114],"adding":[117],"adjustment":[119],"layer":[120],"improve":[122],"regression":[124],"accuracy":[125],"DNN.":[127],"experiments":[131],"show":[132],"that":[133],"proposed":[135],"has":[137],"improved":[138],"PESQ":[140],"SNR":[142],"by":[143],"5%":[144],"15%":[146],"compared":[147],"traditional":[150],"approximation":[152],"method.":[153]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}