{"id":"https://openalex.org/W2900381824","doi":"https://doi.org/10.1109/iwaenc.2018.8521346","title":"Time-Frequency Masking Based Online Speech Enhancement with Multi-Channel Data Using Convolutional Neural Networks","display_name":"Time-Frequency Masking Based Online Speech Enhancement with Multi-Channel Data Using Convolutional Neural Networks","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900381824","doi":"https://doi.org/10.1109/iwaenc.2018.8521346","mag":"2900381824"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047247941","display_name":"Soumitro Chakrabarty","orcid":"https://orcid.org/0000-0002-0846-207X"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Soumitro Chakrabarty","raw_affiliation_strings":["International Audio Laboratories Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Center for Cognitive & Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center for Cognitive & Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanuel A. P. Habets","raw_affiliation_strings":["International Audio Laboratories Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"480"},"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":0.9986000061035156,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8225296139717102},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6962766647338867},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6757754683494568},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6606007814407349},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6313095092773438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4974811375141144},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.488004595041275},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4640352725982666},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43555566668510437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4161722660064697},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2949099540710449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225296139717102},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6962766647338867},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6757754683494568},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6606007814407349},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6313095092773438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4974811375141144},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.488004595041275},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4640352725982666},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43555566668510437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4161722660064697},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2949099540710449},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iwaenc.2018.8521346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-581554","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-581554.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IIS","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/407375","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/407375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1952824372","https://openalex.org/W1982172017","https://openalex.org/W1992879732","https://openalex.org/W1996304098","https://openalex.org/W2030486566","https://openalex.org/W2061074721","https://openalex.org/W2069681747","https://openalex.org/W2095705004","https://openalex.org/W2141998673","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2506203739","https://openalex.org/W2589857635","https://openalex.org/W2599685671","https://openalex.org/W2611943505","https://openalex.org/W2636483419","https://openalex.org/W2964121744","https://openalex.org/W3104757150","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6640825725","https://openalex.org/W6674330103"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W3081694532","https://openalex.org/W1969211203","https://openalex.org/W2770593030","https://openalex.org/W1517958729","https://openalex.org/W2092272653","https://openalex.org/W4321487865","https://openalex.org/W3154990682","https://openalex.org/W4313906399","https://openalex.org/W1996690921"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,21,100],"in":[2],"noisy":[3],"and":[4,63,76,83,129],"reverberant":[5],"conditions":[6,143],"remains":[7],"a":[8,14],"challenging":[9],"task.":[10],"In":[11,95],"this":[12],"work,":[13],"time-frequency":[15],"masking":[16],"based":[17],"method":[18,57,90,109,139],"for":[19,92],"speech":[20,47,99,121],"with":[22,126],"multi":[23,104],"-channel":[24,105],"data":[25],"using":[26],"convolutional":[27],"neural":[28],"networks":[29],"(CNN)":[30],"is":[31,36],"proposed,":[32],"where":[33],"the":[34,40,61,67,88,107,115,119,134,137],"CNN":[35],"trained":[37],"to":[38,97,140],"estimate":[39],"ideal":[41],"ratio":[42],"mask":[43],"by":[44],"discriminating":[45],"directional":[46],"source":[48],"from":[49],"diffuse":[50],"or":[51],"spatially":[52],"uncorrelated":[53],"noise.":[54],"The":[55,78],"proposed":[56,89,108,138],"operates":[58],"on,":[59],"frame-by-frame,":[60],"magnitude":[62],"phase":[64],"components":[65],"of":[66,72,80,118,136],"short-time":[68],"Fourier":[69],"transform":[70],"coefficients":[71],"all":[73],"frequency":[74],"sub-bands":[75],"microphones.":[77],"avoidance":[79],"temporal":[81],"context":[82],"explicit":[84],"feature":[85],"extraction":[86],"makes":[87],"suitable":[91],"online":[93],"implementation.":[94],"contrast":[96],"most":[98],"methods":[101],"that":[102],"utilize":[103],"data,":[106,131],"does":[110],"not":[111],"require":[112],"information":[113],"about":[114],"spatial":[116],"position":[117],"desired":[120],"source.":[122],"Through":[123],"experimental":[124],"evaluation":[125],"both":[127],"simulated":[128],"real":[130],"we":[132],"show":[133],"robustness":[135],"unseen":[141],"acoustic":[142],"as":[144,146],"well":[145],"varying":[147],"noise":[148],"levels.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}