{"id":"https://openalex.org/W3163793923","doi":"https://doi.org/10.1109/icassp39728.2021.9414858","title":"Recent Developments on Espnet Toolkit Boosted By Conformer","display_name":"Recent Developments on Espnet Toolkit Boosted By Conformer","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163793923","doi":"https://doi.org/10.1109/icassp39728.2021.9414858","mag":"3163793923"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Johns Hopkins University","Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104138472","display_name":"Florian Boyer","orcid":null},"institutions":[{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florian Boyer","raw_affiliation_strings":["Airudit","LaBRI, University of Bordeaux"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airudit","institution_ids":[]},{"raw_affiliation_string":"LaBRI, University of Bordeaux","institution_ids":["https://openalex.org/I4210142254","https://openalex.org/I15057530","https://openalex.org/I4210160189"]}]},{"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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Human Dataware Lab. Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Dataware Lab. Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034382743","display_name":"Naoyuki Kamo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kamo","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112122495","display_name":"Jing Shi","orcid":"https://orcid.org/0000-0003-3225-7145"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jing Shi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649112","display_name":"Kun Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wei","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074415592","display_name":"Yuekai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuekai Zhang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5101783173"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":23.6482,"has_fulltext":false,"cited_by_count":197,"citation_normalized_percentile":{"value":0.9963722,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5874","last_page":"5878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.7530160546302795},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7411640882492065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5248587131500244},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4740683436393738},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.47229674458503723},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4066937565803528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3246026635169983},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11626875400543213},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10474878549575806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530160546302795},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7411640882492065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5248587131500244},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4740683436393738},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.47229674458503723},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4066937565803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3246026635169983},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11626875400543213},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10474878549575806},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2127141656","https://openalex.org/W2127851351","https://openalex.org/W2133564696","https://openalex.org/W2407080277","https://openalex.org/W2526425061","https://openalex.org/W2567070169","https://openalex.org/W2734774145","https://openalex.org/W2886180730","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2936774411","https://openalex.org/W2946200149","https://openalex.org/W2948981900","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963542740","https://openalex.org/W2963587345","https://openalex.org/W2963970792","https://openalex.org/W2964110616","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3008191852","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3037217258","https://openalex.org/W3085139254","https://openalex.org/W3097777922","https://openalex.org/W3115011379","https://openalex.org/W3130016944","https://openalex.org/W3150572638","https://openalex.org/W4287667694","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6679434410","https://openalex.org/W6713762819","https://openalex.org/W6731370813","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6755207826","https://openalex.org/W6763608318","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783267081"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0],"this":[1,109],"study,":[2],"we":[3],"present":[4],"recent":[5],"developments":[6],"on":[7,69],"ESPnet:":[8],"End-to-":[9],"End":[10],"Speech":[11],"Processing":[12],"toolkit,":[13],"which":[14],"mainly":[15],"involves":[16],"a":[17,31],"recently":[18],"proposed":[19],"architecture":[20],"called":[21],"Conformer,":[22],"Convolution-augmented":[23],"Transformer.":[24],"This":[25],"paper":[26],"shows":[27],"the":[28,67,79,100,120],"results":[29,73],"for":[30,98,108],"wide":[32],"range":[33],"of":[34,122],"end-":[35],"to-end":[36],"speech":[37,43,46,49],"processing":[38],"applications,":[39],"such":[40],"as":[41],"automatic":[42],"recognition":[44],"(ASR),":[45],"translations":[47],"(ST),":[48],"separation":[50],"(SS)":[51],"and":[52,61,94],"text-to-speech":[53],"(TTS).":[54],"Our":[55,106],"experiments":[56],"reveal":[57],"various":[58],"training":[59],"tips":[60],"significant":[62],"performance":[63],"benefits":[64],"obtained":[65],"with":[66,103],"Conformer":[68],"different":[70],"tasks.":[71],"These":[72],"are":[74,85],"competitive":[75],"or":[76],"even":[77],"outperform":[78],"current":[80],"state-of-art":[81],"Transformer":[82],"models.":[83,105],"We":[84],"preparing":[86,123],"to":[87,112,114],"release":[88],"all-in-one":[89],"recipes":[90],"using":[91],"open":[92],"source":[93],"publicly":[95],"available":[96],"corpora":[97],"all":[99],"above":[101],"tasks":[102],"pre-trained":[104],"aim":[107],"work":[110],"is":[111],"contribute":[113],"our":[115],"research":[116,125],"community":[117],"by":[118],"reducing":[119],"burden":[121],"state-of-the-art":[124],"environments":[126],"usually":[127],"requiring":[128],"high":[129],"resources.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":59},{"year":2022,"cited_by_count":49},{"year":2021,"cited_by_count":36}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}