Transformer-Based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project

dc.contributor.authorLehečka, Jan
dc.contributor.authorPsutka, Josef
dc.contributor.authorPsutka, Josef
dc.date.accessioned2023-01-16T11:00:16Z
dc.date.available2023-01-16T11:00:16Z
dc.date.issued2022
dc.description.abstract-translatedCzech is a very specific language due to its large differences between the formal and the colloquial form of speech. While the formal (written) form is used mainly in official documents, literature, and public speeches, the colloquial (spoken) form is used widely among people in casual speeches. This gap introduces serious problems for ASR systems, especially when training or evaluating ASR models on datasets containing a lot of colloquial speech, such as the MALACH project. In this paper, we are addressing this problem in the light of a new paradigm in end-to-end ASR systems – recently introduced self-supervised audio Transformers. Specifically, we are investigating the influence of colloquial speech on the performance of Wav2Vec 2.0 models and their ability to transcribe colloquial speech directly into formal transcripts. We are presenting results with both formal and colloquial forms in the training transcripts, language models, and evaluation transcripts.en
dc.format12 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationLEHEČKA, J. PSUTKA, J. PSUTKA, J. Transformer-Based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project. In Text, Speech, and Dialogue 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings. Cham: Springer International Publishing, 2022. s. 301-312. ISBN: 978-3-031-16269-5 , ISSN: 0302-9743cs
dc.identifier.doi10.1007/978-3-031-16270-1_25
dc.identifier.isbn978-3-031-16269-5
dc.identifier.issn0302-9743
dc.identifier.obd43936696
dc.identifier.uri2-s2.0-85139084966
dc.identifier.urihttp://hdl.handle.net/11025/50924
dc.language.isoenen
dc.project.IDEF17_048/0007267/InteCom: VaV inteligentních komponent pokročilých technologií pro plzeňskou metropolitní oblastcs
dc.project.ID90140/Velká výzkumná infrastruktura_(J) - e-INFRA CZcs
dc.publisherSpringer International Publishingen
dc.relation.ispartofseriesText, Speech, and Dialogue 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedingsen
dc.rightsPlný text je přístupný v rámci univerzity přihlášeným uživatelům.cs
dc.rights© Springer Nature Switzerland AGen
dc.rights.accessrestrictedAccessen
dc.subject.translatedWav2Vec 2.0en
dc.subject.translatedColloquial speechen
dc.subject.translatedASRen
dc.titleTransformer-Based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Projecten
dc.typekonferenční příspěvekcs
dc.typeConferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
Lehecka_PsutkaJV_PsutkaJ-TransformerBased_Automatic_Speech_TSD_2022.pdf
Size:
796.02 KB
Format:
Adobe Portable Document Format