{"id":"https://openalex.org/W3015339066","doi":"https://doi.org/10.1109/icassp40776.2020.9054298","title":"Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers in the Magnitude and Phase Responses","display_name":"Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers in the Magnitude and Phase Responses","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015339066","doi":"https://doi.org/10.1109/icassp40776.2020.9054298","mag":"3015339066"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5076410694","display_name":"Khandokar Md. Nayem","orcid":"https://orcid.org/0000-0002-4124-4955"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khandokar Md. Nayem","raw_affiliation_strings":["Department of Computer Science, Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054209447","display_name":"Donald S. Williamson","orcid":"https://orcid.org/0000-0002-7997-5403"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald S. Williamson","raw_affiliation_strings":["Department of Computer Science, Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076410694"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40006583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"22","issue":null,"first_page":"6224","last_page":"6228"},"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/T13289","display_name":"Infant Health and Development","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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/magnitude","display_name":"Magnitude (astronomy)","score":0.7872878313064575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7425352931022644},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7054123878479004},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5878994464874268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4769541025161743},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4755789339542389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4584827125072479},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4443942904472351},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2998426556587219},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10433146357536316},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07678717374801636}],"concepts":[{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.7872878313064575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425352931022644},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7054123878479004},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5878994464874268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4769541025161743},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4755789339542389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4584827125072479},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4443942904472351},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2998426556587219},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10433146357536316},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07678717374801636},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1557133539","https://openalex.org/W1635512741","https://openalex.org/W1979099822","https://openalex.org/W2007115401","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2291522532","https://openalex.org/W2291877678","https://openalex.org/W2797110164","https://openalex.org/W2899023680","https://openalex.org/W2941756122","https://openalex.org/W2944209089","https://openalex.org/W2962843322","https://openalex.org/W2963045393","https://openalex.org/W2963317762","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2981253098","https://openalex.org/W4231807801","https://openalex.org/W6662018355","https://openalex.org/W6668037159","https://openalex.org/W6688843265","https://openalex.org/W6696972928","https://openalex.org/W6735429107","https://openalex.org/W6748795944","https://openalex.org/W6755976571","https://openalex.org/W6762220142"],"related_works":["https://openalex.org/W2376418092","https://openalex.org/W2072983018","https://openalex.org/W1016952678","https://openalex.org/W2257644995","https://openalex.org/W1513444457","https://openalex.org/W4311345787","https://openalex.org/W2188141918","https://openalex.org/W3185336960","https://openalex.org/W2042652790","https://openalex.org/W3008584592"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,116],"has":[2],"greatly":[3],"benefited":[4],"from":[5],"deep":[6,12,51],"learning.":[7],"Currently,":[8],"the":[9,39,62,78,97,105,134],"best":[10],"performing":[11],"architectures":[13],"use":[14],"long":[15,27],"short-term":[16],"memory":[17],"(LSTM)":[18],"recurrent":[19,94],"neural":[20],"networks":[21],"(RNNs)":[22],"to":[23,75,100,139],"model":[24,86],"short":[25],"and":[26,41,58,64,81,107,118],"temporal":[28,57,88],"dependencies.":[29],"These":[30],"approaches,":[31],"however,":[32],"underutilize":[33],"or":[34],"ignore":[35],"spectral-level":[36],"dependencies":[37,60,103,123,137],"within":[38,61,104,124],"magnitude":[40,63,106],"phase":[42,65,108],"responses,":[43],"respectively.":[44],"In":[45],"this":[46,85],"paper,":[47],"we":[48,69],"propose":[49],"a":[50,72,125],"learning":[52],"architecture":[53],"that":[54,120,132],"leverages":[55],"both":[56,77],"spectral":[59,102,122,136],"responses.":[66,109],"More":[67],"specifically,":[68],"first":[70],"train":[71],"LSTM":[73],"network":[74],"predict":[76],"spectral-magnitude":[79],"response":[80],"group":[82],"delay,":[83],"where":[84],"captures":[87],"correlations.":[89],"We":[90,110],"then":[91],"introduce":[92],"Markovian":[93],"connections":[95],"in":[96],"output":[98],"layers":[99],"capture":[101],"compare":[111],"our":[112],"approach":[113],"with":[114],"traditional":[115],"approaches":[117,119],"consider":[121],"single":[126],"time":[127],"frame.":[128],"The":[129],"results":[130],"show":[131],"considering":[133],"within-frame":[135],"leads":[138],"improvements.":[140]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}