{"id":"https://openalex.org/W4297841651","doi":"https://doi.org/10.21437/interspeech.2022-10727","title":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding","display_name":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841651","doi":"https://doi.org/10.21437/interspeech.2022-10727"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10727","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10727","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Ju Lu","raw_affiliation_strings":["Academia Sinica, Taipei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei","institution_ids":["https://openalex.org/I84653119"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027035775","display_name":"Chenda Li","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"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":["Universit\u00e0 Politecnica delle Marche, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Politecnica delle Marche, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042385500","display_name":"Yoshiki Masuyama","orcid":"https://orcid.org/0000-0002-5881-0474"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]},{"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":["JP","US"],"is_corresponding":false,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Carnegie Mellon University, USA","Tokyo Metropolitan University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125256","display_name":"Brian Yan","orcid":"https://orcid.org/0000-0002-4160-6282"},"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":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020401831","display_name":"Robin Scheibler","orcid":"https://orcid.org/0000-0002-5205-8365"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Robin Scheibler","raw_affiliation_strings":["LINE Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica, Taipei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"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":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5458","last_page":"5462"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8700250387191772},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7751880884170532},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7279019951820374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6734083294868469},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5232240557670593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47204315662384033},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4356039762496948},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43447184562683105},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42087340354919434},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.41390877962112427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4034344255924225},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3992433249950409},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.34203803539276123},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09493044018745422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8700250387191772},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7751880884170532},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7279019951820374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6734083294868469},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5232240557670593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47204315662384033},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4356039762496948},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43447184562683105},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42087340354919434},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.41390877962112427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4034344255924225},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3992433249950409},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.34203803539276123},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09493044018745422},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10727","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10727","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1506438021","https://openalex.org/W1936725236","https://openalex.org/W2039553327","https://openalex.org/W2089586791","https://openalex.org/W2221409856","https://openalex.org/W2555915854","https://openalex.org/W2558649592","https://openalex.org/W2559260703","https://openalex.org/W2594607416","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2785350307","https://openalex.org/W2902541609","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963488660","https://openalex.org/W2964058413","https://openalex.org/W2982471419","https://openalex.org/W2998616931","https://openalex.org/W3004309045","https://openalex.org/W3015199127","https://openalex.org/W3015306655","https://openalex.org/W3016131876","https://openalex.org/W3016232124","https://openalex.org/W3032514799","https://openalex.org/W3032969657","https://openalex.org/W3035268204","https://openalex.org/W3036237438","https://openalex.org/W3093839391","https://openalex.org/W3096408984","https://openalex.org/W3097627357","https://openalex.org/W3097906045","https://openalex.org/W3100460087","https://openalex.org/W3151851237","https://openalex.org/W3158779859","https://openalex.org/W3162315798","https://openalex.org/W3163217847","https://openalex.org/W3163257865","https://openalex.org/W3165227983","https://openalex.org/W3167533889","https://openalex.org/W3194338569","https://openalex.org/W3197042120","https://openalex.org/W3197832224","https://openalex.org/W3203119473","https://openalex.org/W3207860153","https://openalex.org/W4205689591","https://openalex.org/W4221144097","https://openalex.org/W4224938485","https://openalex.org/W4225270933","https://openalex.org/W4225310539","https://openalex.org/W4225905067","https://openalex.org/W4226071457","https://openalex.org/W4286893829","https://openalex.org/W4287632494","https://openalex.org/W4288029405","https://openalex.org/W4290709727"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W2089240210","https://openalex.org/W284174822"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"recent":[3,27],"progress":[4],"on":[5,73,157],"integrating":[6],"speech":[7,29,48,56,59],"separation":[8],"and":[9,36,62,82,104,145],"enhancement":[10,30,49],"(SSE)":[11],"into":[12],"the":[13,17,114,134],"ESPnet":[14],"toolkit.Compared":[15],"with":[16,32,51,119],"previous":[18],"ESPnet-SE":[19],"work,":[20,154],"numerous":[21],"features":[22],"have":[23],"been":[24,43],"added,":[25],"including":[26,54],"state-of-the-art":[28],"models":[31],"their":[33],"respective":[34],"training":[35],"evaluation":[37],"recipes.Importantly,":[38],"a":[39,123],"new":[40,98],"interface":[41],"has":[42],"designed":[44,75],"to":[45,96,106],"flexibly":[46],"combine":[47],"front-ends":[50,118],"other":[52],"tasks,":[53,84,99],"automatic":[55],"recognition":[57],"(ASR),":[58],"translation":[60],"(ST),":[61],"spoken":[63],"language":[64],"understanding":[65],"(SLU).To":[66],"showcase":[67],"such":[68],"integration,":[69],"we":[70,100],"performed":[71],"experiments":[72],"carefully":[74],"synthetic":[76],"datasets":[77],"for":[78,92,128],"noisy-reverberant":[79],"multichannel":[80,143],"ST":[81,144],"SLU":[83,146],"which":[85,148],"can":[86],"be":[87],"used":[88],"as":[89],"benchmark":[90,107],"corpora":[91],"future":[93],"research.In":[94],"addition":[95],"these":[97],"also":[101],"use":[102],"CHiME-4":[103],"WSJ0-2Mix":[105],"multiand":[108],"single-channel":[109],"SE":[110,117],"approaches.Results":[111],"show":[112],"that":[113],"integration":[115],"of":[116,152],"back-end":[120],"tasks":[121,129],"is":[122,138],"promising":[124],"research":[125],"direction":[126],"even":[127],"besides":[130],"ASR,":[131],"especially":[132],"in":[133],"multi-channel":[135],"scenario.The":[136],"code":[137],"available":[139],"online":[140],"at":[141],"https://github.com/ESPnet/ESPnet.The":[142],"datasets,":[147],"are":[149,155],"another":[150],"contribution":[151],"this":[153],"released":[156],"HuggingFace.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}