Title:	On Comparison of Phonetic Representations for Czech Neural Speech Synthesis
Authors:	Matoušek, Jindřich Tihelka, Daniel
Citation:	MATOUŠEK, J. TIHELKA, D. On Comparison of Phonetic Representations for Czech Neural Speech Synthesis. In Text, Speech, and Dialogue 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings. Cham: Springer International Publishing, 2022. s. 410-422. ISBN: 978-3-031-16269-5 , ISSN: 0302-9743
Issue Date:	2022
Publisher:	Springer International Publishing
Document type:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85139064069 http://hdl.handle.net/11025/50927
ISBN:	978-3-031-16269-5
ISSN:	0302-9743
Keywords in different language:	neural speech synthesis;phonetic representation;phonetic reductions;pause modeling;czech language
Abstract in different language:	In this paper, we investigate two research questions related to the phonetic representation of input text in Czech neural speech synthesis: 1) whether we can afford to reduce the phonetic alphabet, and 2) whether we can remove pauses from phonetic transcription and let the speech synthesis model predict the pause positions itself. In our experiments, three different modern speech synthesis models (FastSpeech 2 + Multi-band MelGAN, Glow-TTS + UnivNet, and VITS) were employed. We have found that the reduced phonetic alphabet outperforms the traditionally used full phonetic alphabet. On the other hand, removing pauses does not help. The presence of pauses (predicted by an external pause prediction tool) in phonetic transcription leads to a slightly better quality of synthetic speech.
Rights:	Plný text je přístupný v rámci univerzity přihlášeným uživatelům. © Springer Nature Switzerland AG
Appears in Collections:	Konferenční příspěvky / Conference papers (NTIS) Konferenční příspěvky / Conference Papers (KKY) OBD

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.