{"id":"https://openalex.org/W2921661700","doi":"https://doi.org/10.23919/apsipa.2018.8659625","title":"Speech Enhancement with Phase Correction based on Modified DNN Architecture","display_name":"Speech Enhancement with Phase Correction based on Modified DNN Architecture","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921661700","doi":"https://doi.org/10.23919/apsipa.2018.8659625","mag":"2921661700"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659625","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5065635383","display_name":"Rui Cheng","orcid":"https://orcid.org/0000-0003-1839-9980"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Cheng","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Bao","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029253113","display_name":"Yang Xiang","orcid":"https://orcid.org/0000-0002-7120-5842"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xiang","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065635383"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.20327521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1222","last_page":"1227"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8457918167114258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.792343020439148},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7766512036323547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7021157145500183},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5313473343849182},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5110960602760315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4804089367389679},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47822970151901245},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4736329913139343},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45227178931236267},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4497952461242676},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4404405951499939},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3523806929588318},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20584255456924438},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.14216920733451843},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06999549269676208}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8457918167114258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792343020439148},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7766512036323547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7021157145500183},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5313473343849182},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5110960602760315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4804089367389679},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47822970151901245},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4736329913139343},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45227178931236267},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4497952461242676},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4404405951499939},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3523806929588318},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20584255456924438},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.14216920733451843},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06999549269676208},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659625","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1790748249","https://openalex.org/W1968939597","https://openalex.org/W1974387177","https://openalex.org/W2041498927","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2095072097","https://openalex.org/W2128653836","https://openalex.org/W2138406058","https://openalex.org/W2141998673","https://openalex.org/W2164427415","https://openalex.org/W2291877678","https://openalex.org/W2403555780","https://openalex.org/W2434171491","https://openalex.org/W2516001803","https://openalex.org/W2749131051","https://openalex.org/W2776384193","https://openalex.org/W2964121744","https://openalex.org/W3124794156","https://openalex.org/W3147539069","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W4375869169","https://openalex.org/W2597829360","https://openalex.org/W2120771489","https://openalex.org/W2921661700","https://openalex.org/W2138406058","https://openalex.org/W2153897396","https://openalex.org/W3110551121","https://openalex.org/W2005805562","https://openalex.org/W2131486661","https://openalex.org/W2089240210"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,20,144],"is":[2,49,62,86,99],"an":[3],"important":[4],"issue":[5],"in":[6],"the":[7,14,45,65,81,90,96,103,133,141],"field":[8],"of":[9,16,68,118],"speech":[10,19,70,92],"signal":[11,123],"processing.":[12],"With":[13],"development":[15],"deep":[17,74],"learning,":[18],"technology":[21],"combined":[22,100,114],"with":[23,115],"neural":[24,75],"network":[25,76],"has":[26,136],"provided":[27],"a":[28,40,52,57,137],"more":[29],"diverse":[30],"solution":[31],"for":[32,146],"this":[33,36,79],"field.":[34],"In":[35,78],"paper,":[37],"we":[38],"present":[39],"new":[41],"approach":[42],"to":[43,88,101,124],"enhance":[44],"noisy":[46],"speech,":[47],"which":[48,61],"recorded":[50],"by":[51,73,110],"single":[53],"channel.":[54],"We":[55],"propose":[56],"phase":[58,97],"correction":[59,98],"method,":[60,80],"based":[63],"on":[64],"joint":[66],"optimization":[67],"clean":[69,91,105],"and":[71,93,95,151],"noise":[72,125],"(DNN).":[77],"ideal":[82],"ratio":[83,126],"masking":[84],"(IRM)":[85],"employed":[87],"estimate":[89],"noise,":[94],"get":[102],"final":[104],"speech.":[106],"Experiments":[107],"are":[108],"conducted":[109],"using":[111],"TIMIT":[112],"corpus":[113],"four":[116],"types":[117],"noises":[119],"at":[120],"three":[121],"different":[122],"(SNR)":[127],"levels.":[128],"The":[129],"results":[130],"show":[131],"that":[132],"proposed":[134],"method":[135,145],"significant":[138],"improvement":[139],"over":[140],"referenced":[142],"DNN-based":[143],"both":[147],"objective":[148],"evaluation":[149,153],"criterion":[150],"subjective":[152],"criterion.":[154]},"counts_by_year":[{"year":2025,"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"}