CNN-TDNN-Based Architecture for Speech Recognition Using Grapheme Models in Bilingual Czech-Slovak Task

dc.contributor.authorPsutka, Josef
dc.contributor.authorŠvec, Jan
dc.contributor.authorPražák, Aleš
dc.date.accessioned2022-03-28T10:00:27Z
dc.date.available2022-03-28T10:00:27Z
dc.date.issued2021
dc.description.abstract-translatedCzech and Slovak languages are very similar, not only in writing but also in phonetic form. This work aims to find a suitable combination of these two languages concerning better recognition results. We would like to show such a contribution on the Malach project. The Malach speech of Holocaust survivors is highly emotional, filled with many disfluencies, heavy accents, age-related coarticulation, and many non-speech events. Due to the nature of the corpus, it is very difficult to find other appropriate data for acoustic modeling, so such a combination can significantly improve the amount of training data. We will discuss the differences between the phoneme and grapheme way of combining Czech with Slovak. We will also compare different architectures of deep neural networks (TDNN, TDNNF, CNN-TDNNF) and tune the optimal topology. The proposed bilingual ASR approach provides a slight improvement over monolingual ASR systems, not only at the phoneme level but also at the grapheme.en
dc.format11 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationPSUTKA, J. ŠVEC, J. PRAŽÁK, A. CNN-TDNN-Based Architecture for Speech Recognition Using Grapheme Models in Bilingual Czech-Slovak Task. In Text, Speech, and Dialogue 24th International Conference, TSD 2021, Olomouc, Czech Republic, September 6–9, 2021, Proceedings. Cham: Springer International Publishing, 2021. s. 523-533. ISBN: 978-3-030-83526-2 , ISSN: 0302-9743cs
dc.identifier.doi10.1007/978-3-030-83527-9_45
dc.identifier.isbn978-3-030-83526-2
dc.identifier.issn0302-9743
dc.identifier.obd43933412
dc.identifier.uri2-s2.0-85115207848
dc.identifier.urihttp://hdl.handle.net/11025/47248
dc.language.isoenen
dc.project.IDTN01000024/Národní centrum kompetence - Kybernetika a umělá inteligencecs
dc.publisherSpringer International Publishingen
dc.relation.ispartofseriesText, Speech, and Dialogue 24th International Conference, TSD 2021, Olomouc, Czech Republic, September 6–9, 2021, Proceedingsen
dc.rightsPlný text je přístupný v rámci univerzity přihlášeným uživatelům.cs
dc.rights© Springeren
dc.rights.accessrestrictedAccessen
dc.subject.translatedSpeech recognitionen
dc.subject.translatedMultilingual trainingen
dc.subject.translatedRobustnessen
dc.subject.translatedAcoustic modelingen
dc.titleCNN-TDNN-Based Architecture for Speech Recognition Using Grapheme Models in Bilingual Czech-Slovak Tasken
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:
Psutka2021_Chapter_CNN-TDNN-BasedArchitectureForS.pdf
Size:
228.83 KB
Format:
Adobe Portable Document Format