{"id":"https://openalex.org/W4385478146","doi":"https://doi.org/10.1109/icasspw59220.2023.10193003","title":"A Reference-Less Quality Metric for Automatic Speech Recognition Via Contrastive-Learning of A Multi-Language Model with Self-Supervision","display_name":"A Reference-Less Quality Metric for Automatic Speech Recognition Via Contrastive-Learning of A Multi-Language Model with Self-Supervision","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385478146","doi":"https://doi.org/10.1109/icasspw59220.2023.10193003"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193003","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5033353054","display_name":"Kamer Ali Y\u00fcksel","orcid":"https://orcid.org/0000-0002-9404-8472"},"institutions":[{"id":"https://openalex.org/I2802212502","display_name":"TiGenix (Spain)","ror":"https://ror.org/0202k4b21","country_code":"ES","type":"company","lineage":["https://openalex.org/I2802212502"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Kamer Ali Yuksel","raw_affiliation_strings":["aiXplain Inc.,Los Gatos,CA,USA","aiXplain Inc., Los Gatos, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiXplain Inc.,Los Gatos,CA,USA","institution_ids":["https://openalex.org/I2802212502"]},{"raw_affiliation_string":"aiXplain Inc., Los Gatos, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109600002","display_name":"Thiago Ferreira","orcid":null},"institutions":[{"id":"https://openalex.org/I2802212502","display_name":"TiGenix (Spain)","ror":"https://ror.org/0202k4b21","country_code":"ES","type":"company","lineage":["https://openalex.org/I2802212502"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Thiago Ferreira","raw_affiliation_strings":["aiXplain Inc.,Los Gatos,CA,USA","aiXplain Inc., Los Gatos, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiXplain Inc.,Los Gatos,CA,USA","institution_ids":["https://openalex.org/I2802212502"]},{"raw_affiliation_string":"aiXplain Inc., Los Gatos, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045881249","display_name":"Ahmet G\u00fcnd\u00fcz","orcid":"https://orcid.org/0000-0001-5589-7167"},"institutions":[{"id":"https://openalex.org/I2802212502","display_name":"TiGenix (Spain)","ror":"https://ror.org/0202k4b21","country_code":"ES","type":"company","lineage":["https://openalex.org/I2802212502"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ahmet Gunduz","raw_affiliation_strings":["aiXplain Inc.,Los Gatos,CA,USA","aiXplain Inc., Los Gatos, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiXplain Inc.,Los Gatos,CA,USA","institution_ids":["https://openalex.org/I2802212502"]},{"raw_affiliation_string":"aiXplain Inc., Los Gatos, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073237528","display_name":"Mohamed Al-Badrashiny","orcid":null},"institutions":[{"id":"https://openalex.org/I2802212502","display_name":"TiGenix (Spain)","ror":"https://ror.org/0202k4b21","country_code":"ES","type":"company","lineage":["https://openalex.org/I2802212502"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mohamed Al-Badrashiny","raw_affiliation_strings":["aiXplain Inc.,Los Gatos,CA,USA","aiXplain Inc., Los Gatos, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiXplain Inc.,Los Gatos,CA,USA","institution_ids":["https://openalex.org/I2802212502"]},{"raw_affiliation_string":"aiXplain Inc., Los Gatos, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065820437","display_name":"Golara Javadi","orcid":"https://orcid.org/0000-0002-8945-1101"},"institutions":[{"id":"https://openalex.org/I2802212502","display_name":"TiGenix (Spain)","ror":"https://ror.org/0202k4b21","country_code":"ES","type":"company","lineage":["https://openalex.org/I2802212502"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Golara Javadi","raw_affiliation_strings":["aiXplain Inc.,Los Gatos,CA,USA","aiXplain Inc., Los Gatos, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiXplain Inc.,Los Gatos,CA,USA","institution_ids":["https://openalex.org/I2802212502"]},{"raw_affiliation_string":"aiXplain Inc., Los Gatos, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2802212502"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2020","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9984999895095825,"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":0.8283628821372986},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7810829877853394},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7569956183433533},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.7359654903411865},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6194957494735718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5874226689338684},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5551789999008179},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5450440049171448},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5427882671356201},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.520345151424408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5193970799446106},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.47339022159576416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283628821372986},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7810829877853394},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7569956183433533},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.7359654903411865},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6194957494735718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874226689338684},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5551789999008179},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5450440049171448},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5427882671356201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.520345151424408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5193970799446106},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.47339022159576416},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icasspw59220.2023.10193003","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1493697127","https://openalex.org/W1494198834","https://openalex.org/W1795658042","https://openalex.org/W2034537249","https://openalex.org/W2058373514","https://openalex.org/W2791556425","https://openalex.org/W2883409523","https://openalex.org/W2972981900","https://openalex.org/W3030437843","https://openalex.org/W3035390927","https://openalex.org/W3095315336","https://openalex.org/W3095373628","https://openalex.org/W3100921325","https://openalex.org/W3119878165","https://openalex.org/W3155072673","https://openalex.org/W3171007011","https://openalex.org/W3174544005","https://openalex.org/W3197041460","https://openalex.org/W4293569541","https://openalex.org/W4311000453","https://openalex.org/W6629800111","https://openalex.org/W6751104502","https://openalex.org/W6768510157","https://openalex.org/W6769263558","https://openalex.org/W6771467084","https://openalex.org/W6785929664","https://openalex.org/W6787673520","https://openalex.org/W6788156848","https://openalex.org/W6788348605","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2050138804","https://openalex.org/W2151348424"],"abstract_inverted_index":{"The":[0,140],"common":[1],"standard":[2],"for":[3,137,148],"quality":[4,40,62],"evaluation":[5],"of":[6,47,63,90],"automatic":[7],"speech":[8,53],"recognition":[9],"(ASR)":[10],"systems":[11],"is":[12,71],"reference-based":[13],"metrics":[14],"such":[15],"as":[16],"the":[17,45,61,100,116,120,149],"Word":[18],"Error":[19],"Rate":[20],"(WER),":[21],"computed":[22],"using":[23],"manual":[24],"ground-truth":[25],"transcriptions":[26],"that":[27],"are":[28,145],"time-consuming":[29],"and":[30,112,127,143],"expensive":[31],"to":[32],"obtain.":[33],"This":[34],"work":[35],"proposes":[36],"a":[37,52,66,77,105],"multi-language":[38],"referenceless":[39,102],"metric,":[41],"which":[42],"allows":[43],"comparing":[44],"performance":[46],"different":[48],"ASR":[49,64,95],"models":[50],"on":[51,84],"dataset":[54],"without":[55],"ground":[56],"truth":[57],"transcriptions.":[58],"To":[59],"estimate":[60],"hypotheses,":[65],"pre-trained":[67],"language":[68],"model":[69,142],"(LM)":[70],"fine-tuned":[72,141],"with":[73,109],"contrastive":[74],"learning":[75,79],"in":[76,97,124],"self-supervised":[78],"manner.":[80],"In":[81],"experiments":[82,144],"conducted":[83],"several":[85],"unseen":[86],"test":[87],"datasets":[88],"consisting":[89],"outputs":[91],"from":[92,119],"top":[93],"commercial":[94],"engines":[96],"various":[98],"languages,":[99],"proposed":[101],"metric":[103,118],"obtains":[104],"much":[106],"higher":[107],"correlation":[108],"WER":[110,130],"scores":[111],"their":[113],"ranks":[114],"than":[115,133],"perplexity":[117],"state-of-art":[121],"multi-lingual":[122],"LM":[123],"all":[125],"experiments,":[126],"also":[128],"reduces":[129],"by":[131],"more":[132],"7%":[134],"when":[135],"used":[136],"ensembling":[138],"hypotheses.":[139],"made":[146],"available":[147],"reproducibility:":[150],"https://github.com/aixplain/NoRefER":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}