{"id":"https://openalex.org/W4386765055","doi":"https://doi.org/10.1109/waspaa58266.2023.10248181","title":"Multichannel Subband-Fullband Gated Convolutional Recurrent Neural Network for Direction-Based Speech Enhancement with Head-Mounted Microphone Arrays","display_name":"Multichannel Subband-Fullband Gated Convolutional Recurrent Neural Network for Direction-Based Speech Enhancement with Head-Mounted Microphone Arrays","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386765055","doi":"https://doi.org/10.1109/waspaa58266.2023.10248181"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5065188041","display_name":"Benjamin E. Stahl","orcid":"https://orcid.org/0000-0002-3169-3167"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Benjamin Stahl","raw_affiliation_strings":["University of Music and Performing Arts,Institute of Electronic Music and Acoustics (IEM),Graz,Austria","Institute of Electronic Music and Acoustics (IEM), University of Music and Performing Arts, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"University of Music and Performing Arts,Institute of Electronic Music and Acoustics (IEM),Graz,Austria","institution_ids":["https://openalex.org/I317320687"]},{"raw_affiliation_string":"Institute of Electronic Music and Acoustics (IEM), University of Music and Performing Arts, Graz, Austria","institution_ids":["https://openalex.org/I317320687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087260049","display_name":"Alois Sontacchi","orcid":"https://orcid.org/0009-0008-9205-209X"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alois Sontacchi","raw_affiliation_strings":["University of Music and Performing Arts,Institute of Electronic Music and Acoustics (IEM),Graz,Austria","Institute of Electronic Music and Acoustics (IEM), University of Music and Performing Arts, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"University of Music and Performing Arts,Institute of Electronic Music and Acoustics (IEM),Graz,Austria","institution_ids":["https://openalex.org/I317320687"]},{"raw_affiliation_string":"Institute of Electronic Music and Acoustics (IEM), University of Music and Performing Arts, Graz, Austria","institution_ids":["https://openalex.org/I317320687"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065188041"],"corresponding_institution_ids":["https://openalex.org/I317320687"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1170579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9984999895095825,"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":0.9921000003814697,"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":0.7913075089454651},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7518630027770996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6625011563301086},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6603398323059082},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6174526810646057},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5579057335853577},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5565071105957031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5155048966407776},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4941714107990265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4626840651035309},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4139881432056427},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41029423475265503},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15487226843833923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913075089454651},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7518630027770996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6625011563301086},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6603398323059082},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6174526810646057},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5579057335853577},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5565071105957031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155048966407776},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4941714107990265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4626840651035309},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4139881432056427},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41029423475265503},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15487226843833923},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":32,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2398042854","https://openalex.org/W2423557781","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2889411318","https://openalex.org/W2901204726","https://openalex.org/W2940275453","https://openalex.org/W2964058413","https://openalex.org/W2973044449","https://openalex.org/W2990433241","https://openalex.org/W2991361823","https://openalex.org/W3015679215","https://openalex.org/W3092796334","https://openalex.org/W3092864146","https://openalex.org/W3097284340","https://openalex.org/W3097945073","https://openalex.org/W3160085755","https://openalex.org/W3160129476","https://openalex.org/W3171278394","https://openalex.org/W3179026300","https://openalex.org/W3191448984","https://openalex.org/W3198156015","https://openalex.org/W4210402803","https://openalex.org/W4221165117","https://openalex.org/W4225604170","https://openalex.org/W4312701366","https://openalex.org/W6770796734","https://openalex.org/W6779192484","https://openalex.org/W6784139575","https://openalex.org/W6797761920","https://openalex.org/W6804452642"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W4386746628","https://openalex.org/W1980687383","https://openalex.org/W2546593254","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,21,24,33,46,58,61,112],"method":[3,82],"for":[4],"direction-based":[5,18],"multichannel":[6],"speech":[7],"enhancement":[8,19],"with":[9,50,73],"head-mounted":[10],"microphone":[11],"arrays.":[12],"To":[13],"target":[14],"the":[15,69,74,77,93,97,106,109],"task":[16],"of":[17,20,29,76,96],"single":[22],"speaker,":[23],"direction-dependent":[25],"feature":[26],"extraction":[27],"composed":[28],"matched":[30],"filters":[31],"and":[32,85,90,101],"maximum-directivity":[34],"beamformer":[35],"is":[36],"employed.":[37],"The":[38,80],"extracted":[39],"features":[40,71],"are":[41],"then":[42],"first":[43],"processed":[44],"by":[45],"subband":[47,78],"neural":[48,66],"network":[49,67],"an":[51],"inplace":[52],"gated":[53,63],"convolutional":[54,64],"recurrent":[55,65],"architecture.":[56],"In":[57],"second":[59],"stage,":[60],"fullband":[62],"processes":[68],"input":[70],"along":[72],"output":[75],"network.":[79],"proposed":[81],"outperforms":[83],"subband-only":[84],"fullband-only":[86],"approaches":[87],"in":[88,111],"PESQ":[89],"SI-SDR":[91],"on":[92],"development":[94],"datasets":[95],"2022/23":[98],"SPEAR":[99],"challenge":[100,110],"was":[102],"rated":[103],"best":[104],"among":[105],"submissions":[107],"to":[108],"paired-comparison":[113],"listening":[114],"experiment.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}