{"id":"https://openalex.org/W2962780374","doi":"https://doi.org/10.21437/interspeech.2018-1456","title":"ESPnet: End-to-End Speech Processing Toolkit","display_name":"ESPnet: End-to-End Speech Processing Toolkit","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2962780374","doi":"https://doi.org/10.21437/interspeech.2018-1456","mag":"2962780374"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1456","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/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/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["NTT Communication Science Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya university;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya university;","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026532766","display_name":"Jiro Nishitoba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiro Nishitoba","raw_affiliation_strings":["Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041236481","display_name":"Yuya Unno","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Unno","raw_affiliation_strings":["Preferred Networks, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004736242","display_name":"Nelson Enrique Yalta Soplin","orcid":"https://orcid.org/0000-0001-7907-0076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson Enrique Yalta Soplin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006131416","display_name":"Jahn Heymann","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jahn Heymann","raw_affiliation_strings":["Paderborn Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn Univ","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738"},"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":"Matthew Wiesner","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/A5071702566","display_name":"Nanxin Chen","orcid":"https://orcid.org/0000-0001-6698-1604"},"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":"Nanxin Chen","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/A5089603211","display_name":"Adithya Renduchintala","orcid":"https://orcid.org/0000-0002-1896-3679"},"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":"Adithya Renduchintala","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103151157","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-5422-6617"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["Doshisha University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University","institution_ids":["https://openalex.org/I133984924"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":89.1859,"has_fulltext":false,"cited_by_count":1348,"citation_normalized_percentile":{"value":0.99952106,"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":"2207","last_page":"2211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.992900013923645,"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":0.992900013923645,"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":0.9337999820709229,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8596144914627075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6872976422309875},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.4845196604728699},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4501839876174927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39061567187309265},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23051846027374268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15969517827033997}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8596144914627075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6872976422309875},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.4845196604728699},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4501839876174927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39061567187309265},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23051846027374268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15969517827033997}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1456","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W2951281592","https://openalex.org/W2166381389","https://openalex.org/W4284893874","https://openalex.org/W3163634122","https://openalex.org/W2919182614","https://openalex.org/W333503034","https://openalex.org/W2054736184","https://openalex.org/W3159728998","https://openalex.org/W2677083173"],"abstract_inverted_index":{"This":[0,67],"paper":[1,68],"introduces":[2],"a":[3,34,56,70],"new":[4],"open":[5,85],"source":[6,86],"platform":[7],"for":[8,47,59],"end-to-end":[9,18],"speech":[10,20,60,64],"processing":[11,65],"named":[12],"ESPnet.":[13],"ESPnet":[14,39,82],"mainly":[15],"focuses":[16],"on":[17],"automatic":[19],"recognition":[21,61],"(ASR),":[22],"and":[23,31,52,62,89],"adopts":[24],"widely-used":[25],"dynamic":[26],"neural":[27],"network":[28],"toolkits,":[29,88],"Chainer":[30],"PyTorch,":[32],"as":[33],"main":[35],"deep":[36],"learning":[37],"engine.":[38],"also":[40],"follows":[41],"the":[42],"Kaldi":[43],"ASR":[44,87,94],"toolkit":[45],"style":[46],"data":[48],"processing,":[49],"feature":[50],"extraction/format,":[51],"recipes":[53],"to":[54],"provide":[55],"complete":[57],"setup":[58],"other":[63,84],"experiments.":[66],"explains":[69],"major":[71,93],"architecture":[72],"of":[73],"this":[74],"software":[75],"platform,":[76],"several":[77],"important":[78],"functionalities,":[79],"which":[80],"differentiate":[81],"from":[83],"experimental":[90],"results":[91],"with":[92],"benchmarks.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":139},{"year":2024,"cited_by_count":157},{"year":2023,"cited_by_count":252},{"year":2022,"cited_by_count":224},{"year":2021,"cited_by_count":268},{"year":2020,"cited_by_count":174},{"year":2019,"cited_by_count":92},{"year":2018,"cited_by_count":10}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
