{"id":"https://openalex.org/W4415135084","doi":"https://doi.org/10.21437/interspeech.2025-318","title":"A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation","display_name":"A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415135084","doi":"https://doi.org/10.21437/interspeech.2025-318"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-318","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.02894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007661580","display_name":"Verena Blaschke","orcid":"https://orcid.org/0000-0002-1082-2740"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Verena Blaschke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020915373","display_name":"Miriam Winkler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miriam Winkler","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119979751","display_name":"Constantin F\u00f6rster","orcid":"https://orcid.org/0000-0003-3390-1051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Constantin F\u00f6rster","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119979752","display_name":"Gabriele Wenger-Glemser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriele Wenger-Glemser","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088832285","display_name":"Barbara Plank","orcid":"https://orcid.org/0000-0002-4394-1965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007661580"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2948,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91188552,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"913","last_page":"917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9933000206947327,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.838699996471405},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5595999956130981},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.47369998693466187},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3479999899864197},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.3075000047683716}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.838699996471405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.621999979019165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5472999811172485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5209000110626221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48159998655319214},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.47369998693466187},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3479999899864197},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-318","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.02894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02894","pdf_url":"https://arxiv.org/pdf/2506.02894","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.02894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02894","pdf_url":"https://arxiv.org/pdf/2506.02894","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415135084.pdf","grobid_xml":"https://content.openalex.org/works/W4415135084.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"Germany":[1,48],"has":[2],"a":[3],"diverse":[4],"landscape":[5],"of":[6,21,38,56,105],"dialects,":[7],"they":[8],"are":[9,25],"underrepresented":[10],"in":[11,41,46],"current":[12],"automatic":[13],"speech":[14,40,83],"recognition":[15],"(ASR)":[16],"research.":[17],"To":[18],"enable":[19],"studies":[20],"how":[22,92],"robust":[23],"models":[24,81],"towards":[26],"dialectal":[27,63,98,123],"variation,":[28],"we":[29],"present":[30],"Betthupferl,":[31],"an":[32,54],"evaluation":[33],"dataset":[34],"containing":[35],"four":[36],"hours":[37],"read":[39],"three":[42],"dialect":[43],"groups":[44],"spoken":[45],"Southeast":[47],"(Franconian,":[49],"Bavarian,":[50],"Alemannic),":[51],"and":[52,64,68,88],"half":[53],"hour":[55],"Standard":[57,65,86],"German":[58,66],"speech.":[59],"We":[60,75],"provide":[61],"both":[62],"transcriptions,":[67],"analyze":[69],"the":[70,94,97,106,122],"linguistic":[71],"differences":[72,90],"between":[73,91],"them.":[74],"benchmark":[76],"several":[77],"multilingual":[78],"state-of-the-art":[79],"ASR":[80,108],"on":[82],"translation":[84],"into":[85],"German,":[87],"find":[89],"much":[93],"output":[95],"resembles":[96],"vs.":[99],"standardized":[100],"transcriptions.":[101],"Qualitative":[102],"error":[103],"analyses":[104],"best":[107],"model":[109],"reveal":[110],"that":[111],"it":[112],"sometimes":[113],"normalizes":[114],"grammatical":[115],"differences,":[116],"but":[117],"often":[118],"stays":[119],"closer":[120],"to":[121],"constructions.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-14T00:00:00"}
