Speaker-Dependent BiLSTM-Based Phrasing

dc.contributor.authorŘezáčková, Markéta
dc.contributor.authorTihelka, Daniel
dc.date.accessioned2021-02-22T11:00:20Z
dc.date.available2021-02-22T11:00:20Z
dc.date.issued2020
dc.description.abstract-translatedPhrase boundary detection is an important part of text-to-speech systems since it ensures more natural speech synthesis outputs. However, the problem of phrasing is ambiguous, especially per speaker and per style. This is the reason why this paper focuses on speaker-dependent phrasing for the purposes of speech synthesis, using a neural network model with a speaker code. We also describe results of a listening test focused on incorrectly detected breaks because it turned out that some mistakes could be actually fine, not wrong.en
dc.format8 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationŘEZÁČKOVÁ, M., TIHELKA, D. Speaker-Dependent BiLSTM-Based Phrasing. In: Text, Speech, and Dialogue 23rd International Conference, TSD 2020, Brno, Czech Republic, September 8-11, 2020, Proceedings. Cham: Springer, 2020. s. 340-347. ISBN 978-3-030-58322-4, ISSN 0302-9743.cs
dc.identifier.doi10.1007/978-3-030-58323-1_37
dc.identifier.isbn978-3-030-58322-4
dc.identifier.issn0302-9743
dc.identifier.obd43930360
dc.identifier.uri2-s2.0-85091141874
dc.identifier.urihttp://hdl.handle.net/11025/42717
dc.language.isoenen
dc.project.IDGA19-19324S/Plně trénovatelná syntéza české řeči z textu s využitím hlubokých neuronových sítícs
dc.project.IDSGS-2019-027/Inteligentní metody strojového vnímání a porozumění 4cs
dc.publisherSpringeren
dc.relation.ispartofseriesText, Speech, and Dialogue 23rd International Conference, TSD 2020, Brno, Czech Republic, September 8-11, 2020, Proceedingsen
dc.rightsPlný text není přístupný.cs
dc.rights© Springeren
dc.rights.accessclosedAccessen
dc.subject.translatedPhrase boundary detection, Text-to-speech system, Neural network, Speaker-dependent phrasinen
dc.titleSpeaker-Dependent BiLSTM-Based Phrasingen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files