{"id":"https://openalex.org/W4402111998","doi":"https://doi.org/10.21437/interspeech.2024-907","title":"Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges","display_name":"Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111998","doi":"https://doi.org/10.21437/interspeech.2024-907"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-907","doi":"https://doi.org/10.21437/interspeech.2024-907","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-907","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.01917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079331687","display_name":"Per Egil Kummervold","orcid":"https://orcid.org/0000-0003-1007-0945","observed_orcids":["https://orcid.org/0000-0003-1007-0945"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Per E Kummervold","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064018105","display_name":"Javier de la Rosa","orcid":"https://orcid.org/0000-0002-9143-5573","observed_orcids":["https://orcid.org/0000-0002-9143-5573"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier de la Rosa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067052872","display_name":"Freddy Wetjen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freddy Wetjen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039170066","display_name":"Rolv-Arild Braaten","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rolv-Arild Braaten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075475532","display_name":"Per Erik Solberg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Per Erik Solberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1027,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82039062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3984","last_page":"3988"},"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/T10860","display_name":"Speech and Audio Processing","score":0.00019999999494757503,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/speech-recognition","display_name":"speech recognition","score":0.8029999732971191},{"id":"https://openalex.org/keywords/whisper","display_name":"Whisper","score":0.6150000095367432},{"id":"https://openalex.org/keywords/speech-to-text","display_name":"speech-to-text","score":0.5860000252723694},{"id":"https://openalex.org/keywords/norwegian-dialects","display_name":"Norwegian dialects","score":0.5329999923706055},{"id":"https://openalex.org/keywords/orthography","display_name":"orthography","score":0.5320000052452087},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.5049999952316284}],"concepts":[{"id":"https://openalex.org/C63428231","wikidata":"https://www.wikidata.org/wiki/Q9043","display_name":"Norwegian","level":2,"score":0.9262793064117432},{"id":"https://openalex.org/C13184196","wikidata":"https://www.wikidata.org/wiki/Q9453","display_name":"Dialectic","level":2,"score":0.7496016621589661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5881940126419067},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21332693099975586},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.15036380290985107},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1384318768978119}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-907","doi":"https://doi.org/10.21437/interspeech.2024-907","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-907","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.01917","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.01917","pdf_url":"https://arxiv.org/pdf/2402.01917","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.01917","doi":"https://doi.org/10.48550/arxiv.2402.01917","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.01917","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.01917","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.01917","pdf_url":"https://arxiv.org/pdf/2402.01917","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111998.pdf","grobid_xml":"https://content.openalex.org/works/W4402111998.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4319862635"],"related_works":["https://openalex.org/W4383469144","https://openalex.org/W7002395075","https://openalex.org/W4386058732","https://openalex.org/W4417338252","https://openalex.org/W7036442620","https://openalex.org/W7134824297","https://openalex.org/W7071133827","https://openalex.org/W7005784676","https://openalex.org/W4415432667","https://openalex.org/W7143273238"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"NB-Whisper,":[3],"an":[4],"adaptation":[5],"of":[6,60],"OpenAI's":[7],"Whisper,":[8],"specifically":[9],"fine-tuned":[10],"for":[11],"Norwegian":[12,31,50],"language":[13],"Automatic":[14],"Speech":[15],"Recognition":[16],"(ASR).":[17],"We":[18,41],"highlight":[19],"its":[20],"key":[21],"contributions":[22],"and":[23,35,68],"summarise":[24],"the":[25,49,65,74],"results":[26],"achieved":[27],"in":[28],"converting":[29],"spoken":[30],"into":[32,39],"written":[33],"forms":[34],"translating":[36],"other":[37],"languages":[38],"Norwegian.":[40],"show":[42],"that":[43],"we":[44],"are":[45],"able":[46],"to":[47,62,71],"improve":[48],"Bokm\u00e5l":[51],"transcription":[52],"by":[53],"OpenAI":[54],"Whisper":[55],"Large-v3":[56],"from":[57,69],"a":[58],"WER":[59],"10.4":[61],"6.6":[63],"on":[64,73],"Fleurs":[66],"Dataset":[67],"6.8":[70],"2.2":[72],"NST":[75],"dataset.":[76]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-09-02T00:00:00"}
