{"id":"https://openalex.org/W2405413469","doi":"https://doi.org/10.21437/interspeech.2015-321","title":"A metric for evaluating speech recognizer output based on human-perception model","display_name":"A metric for evaluating speech recognizer output based on human-perception model","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2405413469","doi":"https://doi.org/10.21437/interspeech.2015-321","mag":"2405413469"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-321","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","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/A5028857766","display_name":"Nobuyasu Itoh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuyasu Itoh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013412274","display_name":"Ryuki Tachibana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryuki Tachibana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083574298","display_name":"Masafumi Nishimura","orcid":"https://orcid.org/0000-0001-7633-9340"},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masafumi Nishimura","raw_affiliation_strings":["SHIZUOKA University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHIZUOKA University","institution_ids":["https://openalex.org/I1298590031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1285","last_page":"1288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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":0.9922999739646912,"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/T12031","display_name":"Speech and dialogue systems","score":0.9912999868392944,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9891999959945679,"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/correlation","display_name":"Correlation","score":0.7007534503936768},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6789692044258118},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6112385392189026},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6089967489242554},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5926371216773987},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5740301012992859},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5725265145301819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5536497831344604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4564798176288605},{"id":"https://openalex.org/keywords/rank-correlation","display_name":"Rank correlation","score":0.4210728406906128},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41494977474212646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27624472975730896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20602533221244812},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11219820380210876}],"concepts":[{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.7007534503936768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6789692044258118},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6112385392189026},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6089967489242554},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5926371216773987},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5740301012992859},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5725265145301819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5536497831344604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564798176288605},{"id":"https://openalex.org/C101601086","wikidata":"https://www.wikidata.org/wiki/Q3753228","display_name":"Rank correlation","level":2,"score":0.4210728406906128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41494977474212646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27624472975730896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20602533221244812},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11219820380210876},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-321","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1626209120","https://openalex.org/W2098318492","https://openalex.org/W2101105183","https://openalex.org/W2120589136","https://openalex.org/W2129018774","https://openalex.org/W2137862343","https://openalex.org/W2160130749","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3171520305","https://openalex.org/W3135126032","https://openalex.org/W1924178503","https://openalex.org/W4308716060","https://openalex.org/W4280648719","https://openalex.org/W4386937079","https://openalex.org/W2901774584"],"abstract_inverted_index":{"Word":[0],"error":[1,5,146],"rate":[2,6],"or":[3],"character":[4,145],"are":[7,21,26,47,77,214],"usually":[8],"used":[9],"as":[10],"the":[11,15,34,38,42,45,69,78,89,92,98,103,107,127,138,153,171,175,178,188,212,215],"metrics":[12,24],"for":[13,28,202,211],"evaluating":[14,203],"accuracy":[16],"of":[17,37,44,80,100,109,140,161,177,217],"speech":[18,204],"recognition.":[19],"These":[20],"naturally-defined":[22],"objective":[23],"and":[25,41,57,85,91,106,117,123,194,220],"helpful":[27],"comparing":[29],"recognition":[30,39,70,205],"methods":[31],"fairly.":[32],"However":[33],"overall":[35],"performance":[36],"systems":[40],"usefulness":[43],"results":[46],"not":[48],"necessarily":[49],"considered.":[50],"To":[51],"address":[52],"this":[53],"problem,":[54],"we":[55,75,96,185,196],"study":[56],"propose":[58],"a":[59,158],"metric":[60],"which":[61,182],"replicates":[62],"human-annotated":[63],"scores":[64,129,143,155,176,190],"using":[65,114,130,157,191],"their":[66],"perception":[67,200],"to":[68,135,170],"results.":[71],"The":[72,166,207],"features":[73,163,193],"that":[74,184,195],"use":[76],"numbers":[79,99,216],"insertion":[81],"errors,":[82,84,102],"deletion":[83],"substitution":[86,218],"errors":[87,219],"in":[88],"characters":[90],"syllables.":[93],"In":[94],"addition":[95],"studied":[97],"consecutive":[101,221],"misrecognized":[104],"keywords,":[105],"locations":[108],"errors.":[110,222],"We":[111],"created":[112],"models":[113],"linear":[115],"regression":[116],"random":[118,159],"forest,":[119],"predicted":[120,154],"human-perceived":[121,189],"scores,":[122],"compared":[124],"them":[125],"with":[126,144,152],"actual":[128],"Spearman\u2019s":[131],"rank-based":[132],"correlation.":[133],"According":[134],"our":[136],"experiments":[137],"correlation":[139,173],"human":[141,179,199],"perceived":[142],"rates":[147],"is":[148,164,168],"0.456,":[149],"while":[150],"those":[151,192],"by":[156],"forest":[160],"10":[162],"0.715.":[165],"latter":[167],"close":[169],"averaged":[172],"between":[174],"subjects,":[180],"0.765,":[181],"suggests":[183],"can":[186,197],"predict":[187],"leverage":[198],"model":[201],"performance.":[206],"important":[208],"factors":[209],"(features)":[210],"prediction":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}