{"id":"https://openalex.org/W7148259249","doi":"https://doi.org/10.1109/asru65441.2025.11434734","title":"VERSA-v2: A Modular and Scalable Toolkit for Speech and Audio Evaluation with Expanded Metrics, Visualization, and LLM Integration","display_name":"VERSA-v2: A Modular and Scalable Toolkit for Speech and Audio Evaluation with Expanded Metrics, Visualization, and LLM Integration","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148259249","doi":"https://doi.org/10.1109/asru65441.2025.11434734"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132803092","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,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125253072","display_name":"Bo-Hao Su","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":"Bo-Hao Su","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/A5067162151","display_name":"Shikhar Bharadwaj","orcid":"https://orcid.org/0009-0003-7202-0502"},"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":"Shikhar Bharadwaj","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/A5132752133","display_name":"Yiwen Zhao","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":"Yiwen Zhao","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/A5132752154","display_name":"Shih-Heng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-Heng Wang","raw_affiliation_strings":["University of Southern California,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132766127","display_name":"Jionghao Hang","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 Hang","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/A5100609726","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0003-2915-6714"},"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":"Haoran Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391700","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-6853-7785"},"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":"Wei Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132751562","display_name":"Wenhao Feng","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":"Wenhao Feng","raw_affiliation_strings":["Renmin University of China,China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,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,China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017970849","display_name":"Nezih Topalo\u011flu","orcid":"https://orcid.org/0000-0003-0525-8900"},"institutions":[{"id":"https://openalex.org/I100072489","display_name":"Yeditepe University","ror":"https://ror.org/025mx2575","country_code":"TR","type":"education","lineage":["https://openalex.org/I100072489"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Nezih Topalo\u011flu","raw_affiliation_strings":["Yeditepe University,Turkey"],"affiliations":[{"raw_affiliation_string":"Yeditepe University,Turkey","institution_ids":["https://openalex.org/I100072489"]}]},{"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/A5132801711","display_name":"Jinchuan Tian","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":"Jinchuan Tian","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/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,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800744","display_name":"Hye-jin Shim","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":"Hye-jin Shim","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/A5132771671","display_name":"Wangyou Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I100072489","display_name":"Yeditepe University","ror":"https://ror.org/025mx2575","country_code":"TR","type":"education","lineage":["https://openalex.org/I100072489"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Yeditepe University,Turkey"],"affiliations":[{"raw_affiliation_string":"Yeditepe University,Turkey","institution_ids":["https://openalex.org/I100072489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132828132","display_name":"Wen-Chin Huang","orcid":null},"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":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132789061","display_name":"Shinji Watanabe","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":"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":4,"institutions_distinct_count":18,"corresponding_author_ids":["https://openalex.org/A5132803092"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87547216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6535000205039978,"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":0.6535000205039978,"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":0.06930000334978104,"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/T10860","display_name":"Speech and Audio Processing","score":0.060600001364946365,"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/modular-design","display_name":"Modular design","score":0.5855000019073486},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5180000066757202},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34779998660087585},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.29660001397132874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073000073432922},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2484000027179718},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.24529999494552612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":19,"referenced_works":["https://openalex.org/W2128301448","https://openalex.org/W2170142018","https://openalex.org/W2898827701","https://openalex.org/W2962780374","https://openalex.org/W3097934054","https://openalex.org/W3160506022","https://openalex.org/W3209059054","https://openalex.org/W4221144124","https://openalex.org/W4283067311","https://openalex.org/W4296068974","https://openalex.org/W4361994820","https://openalex.org/W4392902957","https://openalex.org/W4402112521","https://openalex.org/W4406461271","https://openalex.org/W4406461437","https://openalex.org/W4406461503","https://openalex.org/W4411119792","https://openalex.org/W4415432930","https://openalex.org/W4415433004"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"VERSA-v2,":[2],"a":[3,29,71],"major":[4],"upgrade":[5],"of":[6,10],"the":[7],"Versatile":[8],"Evaluation":[9],"Speech":[11],"and":[12,18,24,37,55,61,74,79,82],"Audio":[13],"(VERSA)":[14],"toolkit":[15],"for":[16,77],"standardized":[17],"scalable":[19],"evaluation":[20,57],"across":[21],"speech,":[22],"audio,":[23],"music":[25],"tasks.":[26],"It":[27],"features":[28],"modular,":[30],"object-oriented":[31],"architecture":[32],"that":[33],"simplifies":[34],"metric":[35],"integration":[36],"now":[38],"supports":[39],"over":[40],"100":[41],"metrics,":[42],"organized":[43],"into":[44],"curated":[45],"task-specific":[46],"packs.":[47],"VERSA-v2":[48,70],"also":[49],"introduces":[50],"interactive":[51],"visualizations,":[52],"per-metric":[53],"profiling,":[54],"prompt-based":[56],"using":[58],"both":[59],"text-":[60],"audio-based":[62],"large":[63],"language":[64],"models":[65],"(LLMs).":[66],"These":[67],"advancements":[68],"make":[69],"robust,":[72],"extensible,":[73],"LLM-enabled":[75],"platform":[76],"comprehensive":[78],"interpretable":[80],"speech":[81],"audio":[83],"evaluation.":[84]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
