{"id":"https://openalex.org/W4372260534","doi":"https://doi.org/10.1109/icassp49357.2023.10095710","title":"Speechlmscore: Evaluating Speech Generation Using Speech Language Model","display_name":"Speechlmscore: Evaluating Speech Generation Using Speech Language Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260534","doi":"https://doi.org/10.1109/icassp49357.2023.10095710"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095710","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":"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/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"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":"Soumi Maiti","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"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","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"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":["JP","US"],"is_corresponding":false,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA","The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5735,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95887533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"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":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.8254594802856445},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7461405992507935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6023492217063904},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5519866943359375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.541217029094696},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5359957814216614},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4898070991039276},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46667611598968506},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45557230710983276},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.448472261428833},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4459571838378906},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42994117736816406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3775081932544708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254594802856445},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7461405992507935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6023492217063904},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5519866943359375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541217029094696},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5359957814216614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4898070991039276},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46667611598968506},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45557230710983276},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.448472261428833},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4459571838378906},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42994117736816406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3775081932544708},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095710","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":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"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":55,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1977556410","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2064675550","https://openalex.org/W2075843680","https://openalex.org/W2093450784","https://openalex.org/W2125114513","https://openalex.org/W2403891086","https://openalex.org/W2473388484","https://openalex.org/W2557915412","https://openalex.org/W2593116425","https://openalex.org/W2936695845","https://openalex.org/W2963035245","https://openalex.org/W2970785793","https://openalex.org/W2972394484","https://openalex.org/W2995181338","https://openalex.org/W3016160783","https://openalex.org/W3024605872","https://openalex.org/W3036601975","https://openalex.org/W3082130377","https://openalex.org/W3097906045","https://openalex.org/W3148101939","https://openalex.org/W3161480375","https://openalex.org/W3176456866","https://openalex.org/W3197580070","https://openalex.org/W3202278141","https://openalex.org/W3209059054","https://openalex.org/W4225956675","https://openalex.org/W4286984129","https://openalex.org/W4292402161","https://openalex.org/W4296068974","https://openalex.org/W4296070211","https://openalex.org/W4297841766","https://openalex.org/W4372259881","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4394671563","https://openalex.org/W4395667732","https://openalex.org/W6631190155","https://openalex.org/W6644682428","https://openalex.org/W6677973343","https://openalex.org/W6729924827","https://openalex.org/W6739901393","https://openalex.org/W6761205521","https://openalex.org/W6777028661","https://openalex.org/W6780218876","https://openalex.org/W6790356757","https://openalex.org/W6797816506","https://openalex.org/W6800937488","https://openalex.org/W6843330092","https://openalex.org/W6846041398","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4200068392","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W596245619","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2022789108","https://openalex.org/W2131711534","https://openalex.org/W2009814707","https://openalex.org/W2105439218"],"abstract_inverted_index":{"While":[0],"human":[1,31,100,120],"evaluation":[2,32,121],"is":[3,14,103],"the":[4,27,71,86,91,112],"most":[5],"reliable":[6],"metric":[7,59,114],"for":[8],"evaluating":[9],"speech":[10,23,63,66,76,125,133],"generation":[11,126],"systems,":[12],"it":[13,80,96],"generally":[15],"costly":[16],"and":[17,44,51,84,102,132],"time-consuming.":[18],"Previous":[19],"studies":[20],"on":[21,41,123],"automatic":[22],"quality":[24],"assessment":[25],"address":[26],"problem":[28],"by":[29,78],"predicting":[30],"scores":[33,122],"with":[34,119],"machine":[35],"learning":[36,43],"models.":[37],"However,":[38],"they":[39],"rely":[40],"supervised":[42],"thus":[45],"suffer":[46],"from":[47],"high":[48],"annotation":[49,101],"costs":[50],"domain-shift":[52],"problems.":[53],"We":[54],"propose":[55],"SpeechLMScore,":[56],"an":[57],"unsupervised":[58],"to":[60],"evaluate":[61],"generated":[62],"using":[64],"a":[65,75,104,116],"language":[67],"model.":[68],"SpeechLMScore":[69],"computes":[70],"average":[72,87],"log-probability":[73],"of":[74,89,93],"signal":[77],"mapping":[79],"into":[81],"discrete":[82],"tokens":[83],"measures":[85],"probability":[88],"generating":[90],"sequence":[92],"tokens.":[94],"Therefore,":[95],"does":[97],"not":[98],"require":[99],"highly":[105],"scalable":[106],"framework.":[107],"Evaluation":[108],"results":[109],"demonstrate":[110],"that":[111],"proposed":[113],"shows":[115],"promising":[117],"correlation":[118],"different":[124],"tasks":[127],"including":[128],"voice":[129],"conversion,":[130],"text-to-speech,":[131],"enhancement.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}