{"id":"https://openalex.org/W4406461306","doi":"https://doi.org/10.1109/slt61566.2024.10832148","title":"ESPnet-EZ: Python-Only ESPnet For Easy Fine-Tuning And Integration","display_name":"ESPnet-EZ: Python-Only ESPnet For Easy Fine-Tuning And Integration","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461306","doi":"https://doi.org/10.1109/slt61566.2024.10832148"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5030925462","display_name":"Masao Someki","orcid":null},"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":true,"raw_author_name":"Masao Someki","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023799668","display_name":"Kwanghee Choi","orcid":"https://orcid.org/0000-0001-5254-1093"},"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":"Kwanghee Choi","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"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":"Siddhant Arora","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055644612","display_name":"William Chen","orcid":"https://orcid.org/0000-0001-8924-5853"},"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":"William Chen","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"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/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":"Samuele Cornell","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113242994","display_name":"Jionghao Han","orcid":null},"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":"Jionghao Han","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085113833","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0001-9309-8331"},"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":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101063912","display_name":"Jiatong Shi","orcid":null},"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":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114369418","display_name":"Vaibhav Srivastav","orcid":null},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Srivastav","raw_affiliation_strings":["Hugging Face,USA"],"affiliations":[{"raw_affiliation_string":"Hugging Face,USA","institution_ids":["https://openalex.org/I4387154989"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5030925462"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3415,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70076127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.9973999857902527,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9927999973297119,"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":0.9726999998092651,"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/python","display_name":"Python (programming language)","score":0.8661308288574219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6888105273246765},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4044435918331146},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.38236576318740845},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.34204810857772827}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8661308288574219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6888105273246765},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4044435918331146},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.38236576318740845},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34204810857772827}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2101105183","https://openalex.org/W2107860279","https://openalex.org/W2191779130","https://openalex.org/W2250342921","https://openalex.org/W2726515241","https://openalex.org/W2755344367","https://openalex.org/W2758950307","https://openalex.org/W2808631503","https://openalex.org/W2962780374","https://openalex.org/W2963532001","https://openalex.org/W2972359262","https://openalex.org/W3016160783","https://openalex.org/W3037217258","https://openalex.org/W3092085609","https://openalex.org/W3095717210","https://openalex.org/W3100460087","https://openalex.org/W3151851237","https://openalex.org/W3167533889","https://openalex.org/W3197478142","https://openalex.org/W3197580070","https://openalex.org/W3197876970","https://openalex.org/W3208743843","https://openalex.org/W3208887030","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210574093","https://openalex.org/W3217767527","https://openalex.org/W4210984894","https://openalex.org/W4225956675","https://openalex.org/W4226103796","https://openalex.org/W4280572880","https://openalex.org/W4297841651","https://openalex.org/W4372260178","https://openalex.org/W4385565440","https://openalex.org/W4385822439","https://openalex.org/W4385822890","https://openalex.org/W4385823192","https://openalex.org/W4386566728","https://openalex.org/W4389315128","https://openalex.org/W4390912444","https://openalex.org/W4391021675","https://openalex.org/W4391021803","https://openalex.org/W4392904805","https://openalex.org/W4395447377","https://openalex.org/W4402111462","https://openalex.org/W4402111799","https://openalex.org/W4402112192","https://openalex.org/W4402667021","https://openalex.org/W4402671610","https://openalex.org/W6631362777","https://openalex.org/W6681703963","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6767671539","https://openalex.org/W6768817161","https://openalex.org/W6769627184","https://openalex.org/W6772349387","https://openalex.org/W6795952400","https://openalex.org/W6796581206","https://openalex.org/W6802659129","https://openalex.org/W6847363464","https://openalex.org/W6858015354","https://openalex.org/W6869560975"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W2207495067","https://openalex.org/W1906486629"],"abstract_inverted_index":{"We":[0],"introduce":[1],"ESPnet-EZ,":[2,94],"an":[3],"extension":[4],"of":[5,18,32,101,110,124],"the":[6,75,99,108,118],"open-source":[7],"speech":[8,19,91],"processing":[9],"toolkit":[10],"ESPnet,":[11,97],"aimed":[12],"at":[13],"quick":[14],"and":[15,30,39,55,57,81,107],"easy":[16,28,41],"development":[17],"models.":[20],"ESPnet-EZ":[21,125],"focuses":[22],"on":[23,36],"two":[24],"major":[25],"aspects:":[26],"(i)":[27],"fine-tuning":[29],"inference":[31],"existing":[33],"ESPnet":[34,61],"models":[35],"various":[37],"tasks":[38],"(ii)":[40],"integration":[42],"with":[43,67],"popular":[44],"deep":[45],"neural":[46],"network":[47],"frameworks":[48],"such":[49],"as":[50],"PyTorch-Lightning,":[51],"Hugging":[52],"Face":[53],"transformers":[54],"datasets,":[56],"Lhotse.":[58],"By":[59],"replacing":[60],"design":[62],"choices":[63],"inherited":[64],"from":[65],"Kaldi":[66],"a":[68,83,90],"Python-only,":[69],"Bash-free":[70],"interface,":[71],"we":[72],"dramatically":[73,116],"reduce":[74],"effort":[76],"required":[77],"to":[78,88,96],"build,":[79],"debug,":[80],"use":[82],"new":[84],"model.":[85],"For":[86],"example,":[87],"fine-tune":[89],"foundation":[92],"model,":[93],"compared":[95],"reduces":[98],"number":[100],"newly":[102],"written":[103],"code":[104,112],"by":[105,113],"2.7x":[106],"amount":[109],"dependent":[111],"6.7x":[114],"while":[115],"reducing":[117],"Bash":[119],"script":[120],"dependencies.":[121],"The":[122],"codebase":[123],"is":[126],"publicly":[127],"available.<sup":[128],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}