{"id":"https://openalex.org/W4406461437","doi":"https://doi.org/10.1109/slt61566.2024.10832289","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs For Audio, Music, and Speech","display_name":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs For Audio, Music, and Speech","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461437","doi":"https://doi.org/10.1109/slt61566.2024.10832289"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832289","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/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":true,"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/A5068192693","display_name":"Jinchuan Tian","orcid":"https://orcid.org/0000-0002-2129-471X"},"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":"Jinchuan Tian","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/A5054879184","display_name":"Yihan Wu","orcid":"https://orcid.org/0000-0002-1202-4208"},"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"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yihan Wu","raw_affiliation_strings":["Carnegie Mellon University","Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"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":"Jee-Weon Jung","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/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Tokyo Metropolitan University"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779022","display_name":"William Chen","orcid":"https://orcid.org/0000-0002-3251-3084"},"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"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101011479","display_name":"Yuning Wu","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"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yuning Wu","raw_affiliation_strings":["Carnegie Mellon University","Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113110576","display_name":"Yuxun Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxun Tang","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038012137","display_name":"Massa Baali","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":"Massa Baali","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/A5092998423","display_name":"Dareen Alharthi","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":"Dareen Alharthi","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/A5115603674","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0002-8948-2856"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruifan Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruifan Deng","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114218702","display_name":"Tejes Srivastava","orcid":null},"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":"Tejes Srivastava","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/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"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":"Haibin Wu","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/A5001277622","display_name":"Alexander Liu","orcid":"https://orcid.org/0000-0002-3985-982X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","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":"Bhiksha Raj","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/A5101665677","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0003-4163-6067"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505571","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0002-2163-7401"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":20,"corresponding_author_ids":["https://openalex.org/A5101063912"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.9508,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94769475,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"562","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.9990000128746033,"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/codec","display_name":"Codec","score":0.8951583504676819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7992544770240784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6712477207183838},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6504843831062317},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.532741129398346},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.4977900981903076},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4439443349838257},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2657001316547394},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.19151338934898376},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12329643964767456}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8951583504676819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992544770240784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6712477207183838},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6504843831062317},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.532741129398346},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.4977900981903076},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4439443349838257},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2657001316547394},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.19151338934898376},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12329643964767456},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832289","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":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":105,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1728888090","https://openalex.org/W2141998673","https://openalex.org/W2726515241","https://openalex.org/W2962780374","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3024605872","https://openalex.org/W3024869864","https://openalex.org/W3081800019","https://openalex.org/W3100460087","https://openalex.org/W3151851237","https://openalex.org/W3153263923","https://openalex.org/W3158762648","https://openalex.org/W3159302906","https://openalex.org/W3160427568","https://openalex.org/W3161236344","https://openalex.org/W3161480375","https://openalex.org/W3163217847","https://openalex.org/W3163243746","https://openalex.org/W3170787215","https://openalex.org/W3180374548","https://openalex.org/W3197580070","https://openalex.org/W3198533616","https://openalex.org/W3203140070","https://openalex.org/W3206375275","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4225956675","https://openalex.org/W4280572880","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4297841651","https://openalex.org/W4297841773","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4319862462","https://openalex.org/W4372260052","https://openalex.org/W4372270198","https://openalex.org/W4372347505","https://openalex.org/W4378501656","https://openalex.org/W4379797396","https://openalex.org/W4380434618","https://openalex.org/W4385565440","https://openalex.org/W4385756463","https://openalex.org/W4385807463","https://openalex.org/W4385822439","https://openalex.org/W4385822683","https://openalex.org/W4385823192","https://openalex.org/W4385823256","https://openalex.org/W4385823416","https://openalex.org/W4387323811","https://openalex.org/W4389524500","https://openalex.org/W4390224291","https://openalex.org/W4391021652","https://openalex.org/W4391021746","https://openalex.org/W4392538788","https://openalex.org/W4392902656","https://openalex.org/W4392903251","https://openalex.org/W4392903389","https://openalex.org/W4392904154","https://openalex.org/W4392909068","https://openalex.org/W4392909101","https://openalex.org/W4392909760","https://openalex.org/W4399425629","https://openalex.org/W4399794707","https://openalex.org/W4400111385","https://openalex.org/W4402111425","https://openalex.org/W4402111456","https://openalex.org/W4402111612","https://openalex.org/W4402111636","https://openalex.org/W4402111669","https://openalex.org/W4402111789","https://openalex.org/W4402111799","https://openalex.org/W4402112388","https://openalex.org/W4402112534","https://openalex.org/W4402112643","https://openalex.org/W4402670057","https://openalex.org/W4406461271","https://openalex.org/W6762931180","https://openalex.org/W6777028661","https://openalex.org/W6778823374","https://openalex.org/W6779090866","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6810673746","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6853611000","https://openalex.org/W6856434366","https://openalex.org/W6857134842","https://openalex.org/W6857589352","https://openalex.org/W6862144568","https://openalex.org/W6869301554","https://openalex.org/W6869945801","https://openalex.org/W6892481026"],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2374470469","https://openalex.org/W2129913000","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2787189739","https://openalex.org/W1911859126","https://openalex.org/W3095556352"],"abstract_inverted_index":{"Neural":[0],"codecs":[1,19],"have":[2,20,43],"become":[3],"crucial":[4],"to":[5,14,24],"recent":[6],"speech":[7,84],"and":[8,29,68,74,83,87],"audio":[9,115],"generation":[10],"research.":[11],"In":[12],"addition":[13],"signal":[15],"compression":[16],"capabilities,":[17],"discrete":[18],"also":[21],"been":[22],"found":[23],"enhance":[25],"downstream":[26,38],"training":[27,73,86],"efficiency":[28],"compatibility":[30],"with":[31,96],"autoregressive":[32],"language":[33],"models.":[34,94],"However,":[35],"as":[36],"extensive":[37],"applications":[39],"are":[40],"investigated,":[41],"challenges":[42],"arisen":[44],"in":[45,80],"ensuring":[46],"fair":[47],"comparisons":[48],"across":[49],"diverse":[50,131],"applications.":[51,132],"To":[52],"address":[53],"these":[54],"issues,":[55],"we":[56,98,119],"present":[57,99],"a":[58,101,107],"new":[59],"open-source":[60],"platform":[61],"ESPnet-Codec,":[62,97],"which":[63,105],"is":[64],"built":[65],"on":[66,70],"ESPnet":[67,128],"focuses":[69],"neural":[71],"codec":[72,93,111],"evaluation.":[75],"ESPnet-Codec":[76,122],"offers":[77],"various":[78],"recipes":[79],"audio,":[81],"music,":[82],"for":[85],"evaluation":[88,103,109,116],"using":[89],"several":[90],"widely":[91],"adopted":[92],"Together":[95],"VERSA,":[100],"standalone":[102],"toolkit,":[104],"provides":[106],"comprehensive":[108],"of":[110],"performance":[112],"over":[113],"20":[114],"metrics.":[117],"Notably,":[118],"demonstrate":[120],"that":[121],"can":[123],"be":[124],"integrated":[125],"into":[126],"six":[127],"tasks,":[129],"supporting":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}