{"id":"https://openalex.org/W3110007102","doi":"https://doi.org/10.1109/cisp-bmei51763.2020.9263673","title":"Segmented Time-Frequency Masking Algorithm for Speech Separation Based on Deep Neural Networks","display_name":"Segmented Time-Frequency Masking Algorithm for Speech Separation Based on Deep Neural Networks","publication_year":2020,"publication_date":"2020-10-17","ids":{"openalex":"https://openalex.org/W3110007102","doi":"https://doi.org/10.1109/cisp-bmei51763.2020.9263673","mag":"3110007102"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei51763.2020.9263673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei51763.2020.9263673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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/A5101518209","display_name":"Xinyu Guo","orcid":"https://orcid.org/0000-0003-1119-4173"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Guo","raw_affiliation_strings":["Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China"],"affiliations":[{"raw_affiliation_string":"Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","institution_ids":["https://openalex.org/I18452120"]},{"raw_affiliation_string":"College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100842303","display_name":"Shifeng Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shifeng Ou","raw_affiliation_strings":["Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China"],"affiliations":[{"raw_affiliation_string":"Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","institution_ids":["https://openalex.org/I18452120"]},{"raw_affiliation_string":"College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112506454","display_name":"Meng Gao","orcid":"https://orcid.org/0000-0003-2422-8328"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Gao","raw_affiliation_strings":["Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China"],"affiliations":[{"raw_affiliation_string":"Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","institution_ids":["https://openalex.org/I18452120"]},{"raw_affiliation_string":"College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101828087","display_name":"Ying Gao","orcid":"https://orcid.org/0000-0002-8816-010X"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Gao","raw_affiliation_strings":["Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China"],"affiliations":[{"raw_affiliation_string":"Yantai University,College of Optoelectronic Information Science and Technology,Yantai,China","institution_ids":["https://openalex.org/I18452120"]},{"raw_affiliation_string":"College of Optoelectronic Information Science and Technology, Yantai University, Yantai, China","institution_ids":["https://openalex.org/I18452120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101518209"],"corresponding_institution_ids":["https://openalex.org/I18452120"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1477946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"445","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.9955999851226807,"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-recognition","display_name":"Speech recognition","score":0.747069239616394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423316240310669},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6510223150253296},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5603200793266296},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5201380848884583},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.510532021522522},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.48070794343948364},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47135013341903687},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.45161205530166626},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4496869146823883},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4408547580242157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4310896694660187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4169728457927704},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3607051968574524},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27590835094451904},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15220898389816284}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.747069239616394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423316240310669},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6510223150253296},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5603200793266296},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5201380848884583},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.510532021522522},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.48070794343948364},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47135013341903687},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.45161205530166626},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4496869146823883},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4408547580242157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4310896694660187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4169728457927704},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3607051968574524},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27590835094451904},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15220898389816284},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cisp-bmei51763.2020.9263673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei51763.2020.9263673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1552314771","https://openalex.org/W1989364685","https://openalex.org/W1995536493","https://openalex.org/W2062470211","https://openalex.org/W2099936868","https://openalex.org/W2100495367","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2154392779","https://openalex.org/W2156376969","https://openalex.org/W2158291955","https://openalex.org/W2168379380","https://openalex.org/W2509674098","https://openalex.org/W2919115771","https://openalex.org/W4231807801","https://openalex.org/W6683066063"],"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/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"In":[0],"view":[1],"of":[2,6,40,64,100,149],"the":[3,37,48,54,61,89,97,101,119,133,140,147],"residual":[4],"problem":[5],"speech":[7,15,57,112,141,154],"background":[8],"noise":[9,20,150],"in":[10,18],"supervised":[11],"model":[12],"based":[13,27,111],"single-channel":[14],"separation":[16,113,155],"algorithm":[17,137],"non-stationary":[19],"environments,":[21],"a":[22,106],"piecewise":[23],"time-frequency":[24,130,135],"masking":[25,131,136],"target":[26,39],"on":[28],"Wiener":[29],"filtering":[30],"principle":[31],"is":[32,94,115],"proposed":[33],"and":[34,68,104,143,145,152],"used":[35,95],"as":[36,96],"training":[38,98],"neural":[41,102,108],"network,":[42,103],"which":[43],"can":[44,138],"not":[45],"only":[46],"track":[47],"SNR":[49],"changes,":[50],"but":[51],"also":[52],"reduce":[53],"damage":[55],"to":[56,117],"quality.":[58],"By":[59],"combing":[60],"four":[62],"features":[63,99],"Relative":[65],"spectral":[66],"transform":[67],"perceptual":[69],"linear":[70],"prediction":[71],"(RASTA-PLP)":[72],"+":[73,78,83],"amplitude":[74],"modulation":[75],"spectrogram":[76],"(AMS)":[77],"Mel-frequency":[79],"cepstral":[80,86],"coefficients":[81],"(MFCC)":[82],"Gammatone":[84],"frequency":[85],"coefficient":[87],"(GFCC),":[88],"extracted":[90],"multi-level":[91],"voice":[92],"information":[93],"then":[105],"deep":[107],"network":[109],"(DNN)":[110],"system":[114],"constructed":[116],"separate":[118],"noisy":[120],"speech.":[121],"The":[122],"experimental":[123],"results":[124],"show":[125],"that:":[126],"compared":[127],"with":[128],"traditional":[129],"methods,":[132],"segmented":[134],"improve":[139],"quality":[142],"clarity,":[144],"achieves":[146],"purpose":[148],"suppression":[151],"better":[153],"performance":[156],"at":[157],"low":[158],"SNR.":[159]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}