{"id":"https://openalex.org/W4225310539","doi":"https://doi.org/10.1109/icassp43922.2022.9747146","title":"Towards Low-Distortion Multi-Channel Speech Enhancement: The ESPNET-Se Submission to the L3DAS22 Challenge","display_name":"Towards Low-Distortion Multi-Channel Speech Enhancement: The ESPNET-Se Submission to the L3DAS22 Challenge","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225310539","doi":"https://doi.org/10.1109/icassp43922.2022.9747146"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747146","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":["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/A5100572838","display_name":"Yen\u2010Ju Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["TW","US"],"is_corresponding":true,"raw_author_name":"Yen-Ju Lu","raw_affiliation_strings":["Carnegie Mellon University,USA","Academia Sinica, Taipei","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Academia Sinica, Taipei","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Università Politecnica delle Marche,Italy"],"affiliations":[{"raw_affiliation_string":"Università Politecnica delle Marche,Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai","Shanghai Jiao Tong University, Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai","Shanghai Jiao Tong University, Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100572838"],"corresponding_institution_ids":["https://openalex.org/I74973139","https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":3.1617,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94143577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9201","last_page":"9205"},"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":0.9988999962806702,"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":0.9950000047683716,"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":0.7151577472686768},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.670971155166626},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6525465250015259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.572247326374054},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.5265973806381226},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5261558890342712},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48619312047958374},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4652726352214813},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.45886677503585815},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4345034956932068},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4324303865432739},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4308132529258728},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.42774030566215515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3660230040550232},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.30802637338638306},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1165948212146759},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0993766188621521},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0959775447845459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151577472686768},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.670971155166626},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6525465250015259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.572247326374054},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.5265973806381226},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5261558890342712},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48619312047958374},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4652726352214813},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.45886677503585815},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4345034956932068},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4324303865432739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4308132529258728},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.42774030566215515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3660230040550232},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30802637338638306},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1165948212146759},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0993766188621521},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0959775447845459},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747146","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2067295501","https://openalex.org/W2141998673","https://openalex.org/W2289480995","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2747732471","https://openalex.org/W2767071179","https://openalex.org/W2803583024","https://openalex.org/W2905402910","https://openalex.org/W2918296821","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962998773","https://openalex.org/W2971458685","https://openalex.org/W3004309045","https://openalex.org/W3009032512","https://openalex.org/W3015372568","https://openalex.org/W3015679215","https://openalex.org/W3015791598","https://openalex.org/W3036601975","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3151596526","https://openalex.org/W3151851237","https://openalex.org/W3171278394","https://openalex.org/W3201698955","https://openalex.org/W3203119473","https://openalex.org/W3209490467","https://openalex.org/W3211779545","https://openalex.org/W3213726885","https://openalex.org/W3213747130","https://openalex.org/W3215005424","https://openalex.org/W3216920799","https://openalex.org/W4205689591","https://openalex.org/W4210402803","https://openalex.org/W4225270933","https://openalex.org/W4226300471","https://openalex.org/W4297841603","https://openalex.org/W6778035800","https://openalex.org/W6780218876","https://openalex.org/W6783462664","https://openalex.org/W6802205285","https://openalex.org/W6803803962"],"related_works":["https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W1971477554","https://openalex.org/W818226659","https://openalex.org/W2923631784","https://openalex.org/W4311414679","https://openalex.org/W2567141277","https://openalex.org/W2130785056","https://openalex.org/W2132841313","https://openalex.org/W2021595906"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,23],"submission":[4],"to":[5,60,83],"the":[6,39,78,89,103,108,116,132,136,147],"L3DAS22":[7],"Challenge":[8],"Task":[9],"1,":[10],"which":[11,106],"consists":[12],"of":[13,22,68,142,146],"speech":[14],"enhancement":[15],"with":[16,34,93],"3D":[17],"Ambisonic":[18],"microphones.":[19],"The":[20,74,125],"core":[21],"approach":[24],"combines":[25],"Deep":[26],"Neural":[27],"Network":[28],"(DNN)":[29],"driven":[30],"complex":[31,62],"spectral":[32,63],"mapping":[33],"linear":[35,52,86,117],"beamformers":[36],"such":[37],"as":[38,99],"multi-frame":[40],"multi-channel":[41],"Wiener":[42],"filter.":[43],"Our":[44],"proposed":[45,126],"system":[46],"has":[47],"two":[48],"DNNs":[49,57],"and":[50,70,88,119],"a":[51,66,85,139],"beamformer":[53,118],"in":[54,131],"between.":[55],"Both":[56],"are":[58,97,122],"trained":[59],"perform":[61],"mapping,":[64],"using":[65],"combination":[67],"waveform":[69],"magnitude":[71],"spectrum":[72],"losses.":[73],"estimated":[75,114],"signal":[76],"from":[77,111],"first":[79,130],"DNN":[80,105,121],"is":[81],"used":[82,98],"drive":[84],"beamformer,":[87],"beamforming":[90],"result,":[91],"together":[92],"this":[94,112],"enhanced":[95],"signal,":[96,115],"extra":[100],"inputs":[101],"for":[102],"second":[104,120],"refines":[107],"estimation.":[109],"Then,":[110],"new":[113],"run":[123],"iteratively.":[124],"method":[127],"was":[128],"ranked":[129],"challenge,":[133],"achieving,":[134],"on":[135],"evaluation":[137],"set,":[138],"ranking":[140],"metric":[141],"0.984,":[143],"versus":[144],"0.833":[145],"challenge":[148],"baseline.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}