{"id":"https://openalex.org/W4372260178","doi":"https://doi.org/10.1109/icassp49357.2023.10096977","title":"Euro: Espnet Unsupervised ASR Open-Source Toolkit","display_name":"Euro: Espnet Unsupervised ASR Open-Source Toolkit","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260178","doi":"https://doi.org/10.1109/icassp49357.2023.10096977"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5072814956","display_name":"Dongji Gao","orcid":"https://orcid.org/0009-0006-8885-3084"},"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":true,"raw_author_name":"Dongji Gao","raw_affiliation_strings":["Johns Hopkins University"],"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/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"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028930617","display_name":"Shun-Po Chuang","orcid":"https://orcid.org/0000-0003-0720-2732"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shun-Po Chuang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"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":"Leibny Paola Garcia","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"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/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"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"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":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072814956"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.222,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82695826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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/T10028","display_name":"Topic Modeling","score":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.838340163230896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878435254096985},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3949491083621979},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3427245020866394},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09907564520835876}],"concepts":[{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.838340163230896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878435254096985},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3949491083621979},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3427245020866394},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09907564520835876}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"},{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2046932483","https://openalex.org/W2058094241","https://openalex.org/W2132991150","https://openalex.org/W2144499799","https://openalex.org/W2401271873","https://openalex.org/W2574132677","https://openalex.org/W2766219058","https://openalex.org/W2802201485","https://openalex.org/W2890536590","https://openalex.org/W2901389167","https://openalex.org/W2933138175","https://openalex.org/W2962780374","https://openalex.org/W2964079874","https://openalex.org/W2995181338","https://openalex.org/W3036601975","https://openalex.org/W3095173472","https://openalex.org/W3095410713","https://openalex.org/W3096338464","https://openalex.org/W3096831136","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3153263923","https://openalex.org/W3162193499","https://openalex.org/W3163793923","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221149170","https://openalex.org/W4287173589","https://openalex.org/W4295312788","https://openalex.org/W4295521014","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6712757354","https://openalex.org/W6735913928","https://openalex.org/W6739901393","https://openalex.org/W6757699909","https://openalex.org/W6766978945","https://openalex.org/W6771812881","https://openalex.org/W6780218876","https://openalex.org/W6784642771","https://openalex.org/W6788727158","https://openalex.org/W6795952400","https://openalex.org/W6809739816"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"This":[0,93],"paper":[1],"describes":[2],"the":[3,22,29,49,95,118],"ESPnet":[4,79],"Unsupervised":[5],"ASR":[6],"Open-source":[7],"Toolkit":[8],"(EURO),":[9],"an":[10],"end-to-end":[11],"open-source":[12,151],"toolkit":[13],"for":[14,54],"unsupervised":[15],"automatic":[16],"speech":[17,38],"recognition":[18],"(UASR).":[19],"EURO":[20,47,75,100,131],"adopts":[21],"state-of-the-art":[23,123],"UASR":[24,55,87,124,149],"learning":[25],"method":[26],"introduced":[27],"by":[28,57],"Wav2vec-U,":[30],"originally":[31],"implemented":[32,77],"at":[33,136],"FAIRSEQ,":[34],"which":[35],"leverages":[36],"self-supervised":[37,68,115],"representations":[39],"and":[40,51,60,70,80,98,121,128,143],"adversarial":[41],"training.":[42],"In":[43],"addition":[44],"to":[45,85,101,105,139],"wav2vec2,":[46],"extends":[48],"functionality":[50],"promotes":[52],"reproducibility":[53],"tasks":[56],"integrating":[58],"S3PRL":[59],"k2,":[61],"resulting":[62],"in":[63,78,108],"flexible":[64],"frontends":[65],"from":[66],"27":[67],"models":[69,116],"various":[71],"graph-based":[72],"decoding":[73],"strategies.":[74],"is":[76],"follows":[81],"its":[82],"unified":[83],"pipeline":[84],"provide":[86],"recipes":[88],"with":[89],"a":[90],"complete":[91],"setup.":[92],"improves":[94],"pipeline\u2019s":[96],"efficiency":[97],"allows":[99],"be":[102,133],"easily":[103],"applied":[104],"existing":[106],"datasets":[107],"ESPnet.":[109],"Extensive":[110],"experiments":[111],"on":[112,126,148],"three":[113],"mainstream":[114],"demonstrate":[117],"toolkit\u2019s":[119],"effectiveness":[120],"achieve":[122],"performance":[125],"TIMIT":[127],"LibriSpeech":[129],"datasets.":[130],"will":[132],"publicly":[134],"available":[135],"https://github.com/espnet/espnet,":[137],"aiming":[138],"promote":[140],"this":[141],"exciting":[142],"emerging":[144],"research":[145],"area":[146],"based":[147],"through":[150],"activity.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}