{"id":"https://openalex.org/W4406461448","doi":"https://doi.org/10.1109/slt61566.2024.10832252","title":"Personalizing Large Sequence-to-Sequence Speech Foundation Models With Speaker Representations","display_name":"Personalizing Large Sequence-to-Sequence Speech Foundation Models With Speaker Representations","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461448","doi":"https://doi.org/10.1109/slt61566.2024.10832252"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/A5080633663","display_name":"Dominik Wagner","orcid":"https://orcid.org/0009-0006-7293-9131"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076479722","display_name":"Ilja Baumann","orcid":"https://orcid.org/0000-0002-1991-3710"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ilja Baumann","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062249053","display_name":"Thomas Ranzenberger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Ranzenberger","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053498662","display_name":"Korbinian Riedhammer","orcid":"https://orcid.org/0000-0003-3582-2154"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Korbinian Riedhammer","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080633663"],"corresponding_institution_ids":["https://openalex.org/I4210100612"],"apc_list":null,"apc_paid":null,"fwci":0.3445,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70208298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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/sequence","display_name":"Sequence (biology)","score":0.762844443321228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421845197677612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5846229791641235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5482460260391235},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5266684889793396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4562550485134125}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.762844443321228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421845197677612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5846229791641235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5482460260391235},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5266684889793396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562550485134125},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt61566.2024.10832252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:4139","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/4139","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320320873","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1562694524","https://openalex.org/W2004488387","https://openalex.org/W2060277733","https://openalex.org/W2079623482","https://openalex.org/W2094147890","https://openalex.org/W2150769028","https://openalex.org/W2402146185","https://openalex.org/W2726515241","https://openalex.org/W2890964092","https://openalex.org/W2908510526","https://openalex.org/W2963381607","https://openalex.org/W2964303773","https://openalex.org/W2972403660","https://openalex.org/W3008371034","https://openalex.org/W3008391559","https://openalex.org/W3036601975","https://openalex.org/W3168867926","https://openalex.org/W3174770825","https://openalex.org/W3176828726","https://openalex.org/W3201225328","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225742484","https://openalex.org/W4226098957","https://openalex.org/W4297841331","https://openalex.org/W4311000453","https://openalex.org/W4319750153","https://openalex.org/W4323066695","https://openalex.org/W4372342485","https://openalex.org/W4377130946","https://openalex.org/W4377372369","https://openalex.org/W4385245566","https://openalex.org/W4385807419","https://openalex.org/W4385807453","https://openalex.org/W4385823248","https://openalex.org/W4385987622","https://openalex.org/W4387323811","https://openalex.org/W4388718054","https://openalex.org/W4390047809","https://openalex.org/W4391021584","https://openalex.org/W4391021664","https://openalex.org/W4391871574","https://openalex.org/W4392903087","https://openalex.org/W4392909818","https://openalex.org/W4401042284","https://openalex.org/W6633504797","https://openalex.org/W6682600690","https://openalex.org/W6697030134","https://openalex.org/W6757817989","https://openalex.org/W6759579507","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6803034309","https://openalex.org/W6846218908","https://openalex.org/W6847363464","https://openalex.org/W6852818750","https://openalex.org/W6853249747","https://openalex.org/W6856434366","https://openalex.org/W6859099255","https://openalex.org/W6859529408","https://openalex.org/W6861489518"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2777605427","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,60],"present":[1],"a":[2,42,156],"method":[3,63],"to":[4,48,64,104,113,121],"personalize":[5],"large":[6],"transformer-based":[7],"encoder-decoder":[8],"speech":[9,68,93],"foundation":[10],"models":[11],"without":[12],"the":[13,18,34,38,50,66,133,140,160],"need":[14],"for":[15],"changes":[16,147],"in":[17,148],"underlying":[19],"model":[20],"structure":[21],"or":[22],"training":[23],"from":[24,132,152],"scratch.":[25],"This":[26],"is":[27],"achieved":[28],"by":[29],"projecting":[30],"speaker-specific":[31],"information":[32,52,56],"into":[33],"latent":[35],"space":[36],"of":[37,71,87,111,119,163],"transformer":[39],"decoder":[40],"via":[41,57],"small":[43],"neural":[44],"network":[45],"and":[46,75,94,115,145],"learning":[47],"process":[49],"speaker":[51],"along":[53],"with":[54],"domain-specific":[55],"parameter-efficient":[58],"finetuning.":[59],"use":[61],"this":[62],"improve":[65],"automatic":[67],"recognition":[69],"results":[70],"spoken":[72],"academic":[73,92,98,164],"German":[74,91],"English.":[76],"Our":[77],"approach":[78],"yields":[79,139],"average":[80],"relative":[81,108],"word":[82],"error":[83],"rate":[84],"(WER)":[85],"improvements":[86,110,144],"approximately":[88],"29%":[89],"on":[90,96,123,159],"25%":[95],"English":[97],"speech.":[99,125],"It":[100],"also":[101],"translates":[102],"well":[103],"conversational":[105],"speech,":[106],"achieving":[107],"WER":[109],"up":[112,120],"36%,":[114],"demonstrates":[116],"modest":[117],"gains":[118],"5%":[122],"read":[124],"Moreover,":[126],"we":[127],"observe":[128],"that":[129,146],"incorporating":[130],"utterances":[131],"recent":[134],"past":[135],"as":[136],"personalization":[137,161],"context":[138],"most":[141],"significant":[142],"overall":[143],"voice":[149],"characteristics":[150],"resulting":[151],"prolonged":[153],"speaking":[154],"have":[155],"minimal":[157],"effect":[158],"quality":[162],"lectures.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}