{"id":"https://openalex.org/W7167617536","doi":"https://doi.org/10.48550/arxiv.2607.03207","title":"S-DiverSe: Spanish Diverse Speech","display_name":"S-DiverSe: Spanish Diverse Speech","publication_year":2026,"publication_date":"2026-07-03","ids":{"openalex":"https://openalex.org/W7167617536","doi":"https://doi.org/10.48550/arxiv.2607.03207"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.03207","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.03207","pdf_url":"https://arxiv.org/pdf/2607.03207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.03207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129689548","display_name":"Fernando L\u00f3pez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4402554107","display_name":"Telef\u00f3nica Innovaci\u00f3n Digital (Spain)","ror":"https://ror.org/03t5r9r41","country_code":"ES","type":"company","lineage":["https://openalex.org/I4402554107"]},{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"L\u00f3pez, Fernando","raw_affiliation_strings":["Scientific Research , Telef\u00f3nica Innovaci\u00f3n Digital , Spain","Universidad Aut\u00f3noma de Madrid , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scientific Research , Telef\u00f3nica Innovaci\u00f3n Digital , Spain","institution_ids":["https://openalex.org/I4402554107"]},{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid , Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032105339","display_name":"Fernando Ib\u00e1\u00f1ez","orcid":"https://orcid.org/0000-0002-5593-0892","observed_orcids":["https://orcid.org/0000-0002-5593-0892"]},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Iba\u00f1ez, Fernando","raw_affiliation_strings":["Universidad Aut\u00f3noma de Madrid , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid , Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140177490","display_name":"Ana Mart\u00ednez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mart\u00ednez, Ana","raw_affiliation_strings":["Universidad Aut\u00f3noma de Madrid , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid , Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140206526","display_name":"Iv\u00e1n Alonso","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alonso, Iv\u00e1n","raw_affiliation_strings":["Universidad Aut\u00f3noma de Madrid , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid , Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133172634","display_name":"Pablo G\u00f3mez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4402554107","display_name":"Telef\u00f3nica Innovaci\u00f3n Digital (Spain)","ror":"https://ror.org/03t5r9r41","country_code":"ES","type":"company","lineage":["https://openalex.org/I4402554107"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"G\u00f3mez, Pablo","raw_affiliation_strings":["Scientific Research , Telef\u00f3nica Innovaci\u00f3n Digital , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scientific Research , Telef\u00f3nica Innovaci\u00f3n Digital , Spain","institution_ids":["https://openalex.org/I4402554107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008468618","display_name":"Santosh Kesiraju","orcid":"https://orcid.org/0000-0002-3725-742X","observed_orcids":["https://orcid.org/0000-0002-3725-742X"]},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Kesiraju, Santosh","raw_affiliation_strings":["Brno University of Technology , Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology , Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109759968","display_name":"Jordi Palac\u00edn Luque","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4402554107","display_name":"Telef\u00f3nica Innovaci\u00f3n Digital (Spain)","ror":"https://ror.org/03t5r9r41","country_code":"ES","type":"company","lineage":["https://openalex.org/I4402554107"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luque, Jordi","raw_affiliation_strings":["Scientific Research , Telef\u00f3nica Innovaci\u00f3n Digital , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scientific Research , Telef\u00f3nica Innovaci\u00f3n Digital , Spain","institution_ids":["https://openalex.org/I4402554107"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9994999766349792,"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":0.9994999766349792,"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/T10863","display_name":"Voice and Speech Disorders","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/neurological-speech-disorders","display_name":"neurological speech disorders","score":0.6079999804496765},{"id":"https://openalex.org/keywords/amyotrophic-lateral-sclerosis","display_name":"amyotrophic lateral sclerosis","score":0.9900000095367432},{"id":"https://openalex.org/keywords/parkinson-s-disease","display_name":"Parkinson's disease","score":1.0},{"id":"https://openalex.org/keywords/stroke","display_name":"stroke","score":0.9760000109672546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7129999995231628},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.6259999871253967},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8040000200271606},{"id":"https://openalex.org/keywords/in-the-wild-speech","display_name":"in-the-wild speech","score":0.7570000290870667}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6064000129699707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5591999888420105},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49059998989105225},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4000000059604645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C2779642007","wikidata":"https://www.wikidata.org/wiki/Q1282114","display_name":"Speech disorder","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C2780596555","wikidata":"https://www.wikidata.org/wiki/Q206901","display_name":"Amyotrophic lateral sclerosis","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3142000138759613},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.03207","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.03207","pdf_url":"https://arxiv.org/pdf/2607.03207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.03207","doi":"https://doi.org/10.48550/arxiv.2607.03207","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03207","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.03207","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.03207","pdf_url":"https://arxiv.org/pdf/2607.03207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.46810001134872437,"display_name":"Good health and well-being"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7167617536.pdf","grobid_xml":"https://content.openalex.org/works/W7167617536.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7169877215","https://openalex.org/W7037765566","https://openalex.org/W6928255161","https://openalex.org/W3159719190","https://openalex.org/W7155067931","https://openalex.org/W7163318430","https://openalex.org/W7161737243","https://openalex.org/W4223646484","https://openalex.org/W7133534738","https://openalex.org/W7204707996"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,11,33],"recognition":[2],"(ASR)":[3],"has":[4],"advanced":[5],"remarkably":[6],"for":[7,71,104,113],"standard":[8],"speech,":[9],"yet":[10],"affected":[12,73],"by":[13],"neurological":[14,106],"conditions":[15],"remains":[16],"a":[17,25],"challenge.":[18],"We":[19,76],"present":[20],"S-DiverSe":[21,62],"(Spanish":[22],"Diverse":[23],"Speech),":[24],"corpus":[26],"of":[27,30],"3.2":[28],"hours":[29],"in-the-wild":[31,115],"Spanish":[32,74,107,116],"from":[34],"22":[35],"speakers":[36],"with":[37,53],"amyotrophic":[38],"lateral":[39],"sclerosis,":[40],"Parkinson's":[41],"disease,":[42],"and":[43,60,69,83],"stroke.":[44],"The":[45],"dataset":[46],"contains":[47],"444":[48],"manually":[49],"transcribed":[50],"audio":[51],"segments":[52],"metadata":[54],"on":[55],"speaker":[56],"sex,":[57],"disease":[58],"type,":[59],"intelligibility.":[61],"is":[63,99],"designed":[64],"to":[65],"support":[66],"ASR":[67,86],"evaluation":[68],"development":[70],"neurologically":[72],"speech.":[75,108],"describe":[77],"the":[78,111],"dataset,":[79],"analyze":[80],"its":[81],"composition,":[82],"report":[84],"baseline":[85],"results":[87],"alongside":[88],"initial":[89],"adaptation":[90],"experiments.":[91],"Our":[92],"findings":[93],"reveal":[94],"that":[95],"heuristic":[96],"text":[97],"post-processing":[98],"more":[100],"robust":[101],"than":[102],"fine-tuning":[103],"out-of-domain":[105],"This":[109],"underscores":[110],"need":[112],"dedicated":[114],"benchmarks.":[117]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-08T00:00:00"}
