{"id":"https://openalex.org/W4221150601","doi":"https://doi.org/10.1109/icassp43922.2022.9747521","title":"HGCN: Harmonic Gated Compensation Network for Speech Enhancement","display_name":"HGCN: Harmonic Gated Compensation Network for Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221150601","doi":"https://doi.org/10.1109/icassp43922.2022.9747521"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747521","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.12755","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080726804","display_name":"Tian\u2010Rui Wang","orcid":"https://orcid.org/0000-0003-1068-0321"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["Beijing Jiaotong University,Institute of Information Science,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Institute of Information Science,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033247734","display_name":"Wei\u2010Ping Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Zhu","raw_affiliation_strings":["Beijing Jiaotong University,Institute of Information Science,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Institute of Information Science,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016304163","display_name":"Yingying Gao","orcid":"https://orcid.org/0000-0002-4730-9668"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Gao","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032367559","display_name":"Shilei Zhang","orcid":"https://orcid.org/0000-0001-8169-0098"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080726804"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.1224,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20119647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9836000204086304,"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":0.9836000204086304,"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/T10863","display_name":"Voice and Speech Disorders","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.003700000001117587,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.7277393341064453},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.7082153558731079},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.6980048418045044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.626763105392456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5755148530006409},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4954928159713745},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.49300524592399597},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47013431787490845},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3769689202308655},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.28416943550109863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27455875277519226},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19259628653526306},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15029913187026978},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.100677490234375},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07321462035179138},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0709121823310852}],"concepts":[{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.7277393341064453},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.7082153558731079},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.6980048418045044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.626763105392456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5755148530006409},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4954928159713745},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49300524592399597},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47013431787490845},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3769689202308655},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28416943550109863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27455875277519226},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19259628653526306},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15029913187026978},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.100677490234375},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07321462035179138},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0709121823310852},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747521","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.12755","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.12755","pdf_url":"https://arxiv.org/pdf/2201.12755","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2201.12755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2201.12755","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/7psr-cp62","is_oa":true,"landing_page_url":"https://doi.org/10.17023/7psr-cp62","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.12755","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.12755","pdf_url":"https://arxiv.org/pdf/2201.12755","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221150601.pdf","grobid_xml":"https://content.openalex.org/works/W4221150601.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2004163116","https://openalex.org/W2043756190","https://openalex.org/W2064675550","https://openalex.org/W2121294245","https://openalex.org/W2151484683","https://openalex.org/W2718615637","https://openalex.org/W2750153721","https://openalex.org/W2888924982","https://openalex.org/W2900445934","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2963351448","https://openalex.org/W2982763192","https://openalex.org/W2996807748","https://openalex.org/W2998161426","https://openalex.org/W3096408984","https://openalex.org/W3198680319","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6762182681","https://openalex.org/W6772622344","https://openalex.org/W6796856108","https://openalex.org/W6800095336"],"related_works":["https://openalex.org/W15813549","https://openalex.org/W12824818","https://openalex.org/W6558424","https://openalex.org/W363116","https://openalex.org/W9001339","https://openalex.org/W11924840","https://openalex.org/W17764442","https://openalex.org/W8932171","https://openalex.org/W14961697","https://openalex.org/W177064"],"abstract_inverted_index":{"Mask":[0],"processing":[1],"in":[2,126],"the":[3,8,15,30,60,79,89,97,102,109,127],"time-frequency":[4],"(T-F)":[5],"domain":[6],"through":[7],"neural":[9],"network":[10,49,82],"has":[11],"been":[12],"one":[13],"of":[14,62,123],"mainstreams":[16],"for":[17,25],"single-channel":[18],"speech":[19],"enhancement.":[20],"However,":[21],"it":[22],"is":[23,93],"hard":[24],"most":[26],"models":[27],"to":[28,58,78,84,95,100,107],"handle":[29],"situation":[31],"when":[32],"harmonics":[33],"are":[34],"partially":[35],"masked":[36],"by":[37],"noise.":[38],"To":[39],"tackle":[40],"this":[41],"challenge,":[42],"we":[43,67],"propose":[44],"a":[45,53,121],"harmonic":[46,55,63,86,90],"gated":[47],"compensation":[48,98],"(HGCN).":[50],"We":[51],"design":[52],"high-resolution":[54],"integral":[56],"spectrum":[57],"improve":[59],"accuracy":[61],"locations":[64],"prediction.":[65],"Then":[66],"add":[68],"voice":[69],"activity":[70],"detection":[71,76],"(VAD)":[72],"and":[73],"voiced":[74],"region":[75],"(VRD)":[77],"convolutional":[80],"recurrent":[81],"(CRN)":[83],"filter":[85],"locations.":[87],"Finally,":[88],"gating":[91],"mechanism":[92],"used":[94],"guide":[96],"model":[99],"adjust":[101],"coarse":[103],"results":[104],"from":[105],"CRN":[106],"obtain":[108],"refinedly":[110],"enhanced":[111],"results.":[112],"Our":[113],"experiments":[114],"show":[115],"HGCN":[116],"achieves":[117],"substantial":[118],"gain":[119],"over":[120],"number":[122],"advanced":[124],"approaches":[125],"community.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2022-04-03T00:00:00"}
