{"id":"https://openalex.org/W4385822823","doi":"https://doi.org/10.21437/interspeech.2023-1079","title":"How to Estimate Model Transferability of Pre-Trained Speech Models?","display_name":"How to Estimate Model Transferability of Pre-Trained Speech Models?","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822823","doi":"https://doi.org/10.21437/interspeech.2023-1079"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1079","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5006382467","display_name":"Zih-Ching Chen","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":"Zih-Ching Chen","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374360","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-6709-0942"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2800444561","display_name":"Atlanta Technical College","ror":"https://ror.org/01s3vfp47","country_code":"US","type":"education","lineage":["https://openalex.org/I2800444561"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Google, USA","Georgia Tech, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Georgia Tech, USA","institution_ids":["https://openalex.org/I2800444561","https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049929716","display_name":"Nanxin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nanxin Chen","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo-Yiin Chang","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"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":"Hung-yi Lee","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara Sainath","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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":0.9972000122070312,"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/transferability","display_name":"Transferability","score":0.8641429543495178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7457292079925537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5114197134971619},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.453460156917572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4290422201156616},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4249511957168579},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2159472405910492},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.0894230306148529}],"concepts":[{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.8641429543495178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457292079925537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5114197134971619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.453460156917572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4290422201156616},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4249511957168579},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2159472405910492},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0894230306148529},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1079","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2108598243","https://openalex.org/W2187089797","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2797583228","https://openalex.org/W2896457183","https://openalex.org/W2970112944","https://openalex.org/W2981848390","https://openalex.org/W2982343573","https://openalex.org/W3005343217","https://openalex.org/W3007522628","https://openalex.org/W3015213852","https://openalex.org/W3036601975","https://openalex.org/W3042317849","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3112034174","https://openalex.org/W3133604157","https://openalex.org/W3154806625","https://openalex.org/W3172443934","https://openalex.org/W3186596101","https://openalex.org/W3195577433","https://openalex.org/W3196974791","https://openalex.org/W3197580070","https://openalex.org/W3204696009","https://openalex.org/W3209059054","https://openalex.org/W3215322745","https://openalex.org/W4225274946","https://openalex.org/W4226380987","https://openalex.org/W4256161595","https://openalex.org/W4285144981","https://openalex.org/W4287198862","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4309427288","https://openalex.org/W4311000453","https://openalex.org/W4312903743","https://openalex.org/W4319862642","https://openalex.org/W4372346241","https://openalex.org/W4375869211","https://openalex.org/W4385484947"],"related_works":["https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W1569841287","https://openalex.org/W1512718085"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"introduce":[4],"a":[5,60,89,116],"\"score-based":[6],"assessment\"":[7],"framework":[8,45,100,107],"for":[9,18,37,121],"estimating":[10],"the":[11,38,42],"transferability":[12,48,106],"of":[13,53],"pre-trained":[14],"speech":[15,68,75,123],"models":[16,55,69,76],"(PSMs)":[17],"fine-tuning":[19,102],"target":[20],"tasks.We":[21],"leverage":[22],"upon":[23],"two":[24],"representation":[25],"theories,":[26],"Bayesian":[27],"likelihood":[28],"estimation":[29,99],"and":[30,73,81,94,101,112,118],"optimal":[31],"transport,":[32],"to":[33],"generate":[34],"rank":[35,92],"scores":[36,49],"PSM":[39],"candidates":[40],"using":[41,84],"extracted":[43],"representations.Our":[44],"efficiently":[46],"computes":[47],"without":[50],"actual":[51],"finetuning":[52],"candidate":[54],"or":[56],"layers":[57],"by":[58],"making":[59,114],"temporal":[61],"independent":[62],"hypothesis.We":[63],"evaluate":[64],"some":[65],"popular":[66],"supervised":[67],"(e.g.,":[70,77],"Conformer":[71],"RNN-Transducer)":[72],"selfsupervised":[74],"HuBERT)":[78],"in":[79],"cross-layer":[80],"cross-model":[82],"settings":[83],"public":[85],"data.Experimental":[86],"results":[87],"show":[88],"high":[90],"Spearman's":[91],"correlation":[93],"low":[95],"p-value":[96],"between":[97],"our":[98],"ground":[103],"truth.Our":[104],"proposed":[105],"requires":[108],"less":[109],"computational":[110],"time":[111],"resources,":[113],"it":[115],"resource-saving":[117],"timeefficient":[119],"approach":[120],"tuning":[122],"foundation":[124],"models.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}