{"id":"https://openalex.org/W4393929753","doi":"https://doi.org/10.48550/arxiv.2404.01737","title":"Transfer Learning from Whisper for Microscopic Intelligibility\n Prediction","display_name":"Transfer Learning from Whisper for Microscopic Intelligibility\n Prediction","publication_year":2024,"publication_date":"2024-04-02","ids":{"openalex":"https://openalex.org/W4393929753","doi":"https://doi.org/10.48550/arxiv.2404.01737"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2404.01737","pdf_url":"https://arxiv.org/pdf/2404.01737","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.01737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023319832","display_name":"Paul Best","orcid":"https://orcid.org/0000-0003-4996-0726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Best, Paul","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076491406","display_name":"Santiago Cuervo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cuervo, Santiago","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marxer, Ricard","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":{"min":0,"max":78},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.8957,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.8957,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5925469},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5902253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.62685925},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5925469},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5902253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36798552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3370731},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04678154},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2404.01737","pdf_url":"https://arxiv.org/pdf/2404.01737","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2404.01737","pdf_url":"https://arxiv.org/pdf/2404.01737","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3123837699","https://openalex.org/W2748952813","https://openalex.org/W2478288626","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Macroscopic":[0],"intelligibility":[1,16,80,128],"models":[2,17,34,43],"predict":[3,111],"the":[4,62,83,91,117],"expected":[5],"human":[6],"word-error-rate":[7],"for":[8,44,54,74,78,126],"a":[9,69,96,101],"given":[10],"speech-in-noise":[11],"stimulus.":[12],"In":[13,57],"contrast,":[14],"microscopic":[15,55,79,127],"aim":[18],"to":[19,106,110],"make":[20],"fine-grained":[21],"predictions":[22],"about":[23],"listeners'":[24,112],"perception,":[25],"e.g.":[26],"predicting":[27],"phonetic":[28],"or":[29],"lexical":[30,86],"responses.":[31,87,113],"State-of-the-art":[32],"macroscopic":[33],"use":[35,63],"transfer":[36,65],"learning":[37,42,66,72,123],"from":[38,67],"large":[39,120],"scale":[40,121],"deep":[41,71,122],"speech":[45,76],"processing,":[46],"whereas":[47],"such":[48],"methods":[49,125],"have":[50],"rarely":[51],"been":[52],"used":[53],"modeling.":[56],"this":[58],"paper,":[59],"we":[60],"study":[61],"of":[64,85,104,119],"Whisper,":[68],"state-of-the-art":[70],"model":[73],"automatic":[75],"recognition,":[77],"prediction":[81],"at":[82],"level":[84],"Our":[88,114],"method":[89],"outperforms":[90],"considered":[92],"baselines,":[93],"even":[94],"in":[95],"zero-shot":[97],"setup,":[98],"and":[99],"yields":[100],"relative":[102],"improvement":[103],"up":[105],"66\\%":[107],"when":[108],"fine-tuned":[109],"results":[115],"showcase":[116],"promise":[118],"based":[124],"prediction.":[129]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4393929753","counts_by_year":[],"updated_date":"2025-04-10T07:30:31.560646","created_date":"2024-04-05"}