Title:	How Much End-to-End is Tacotron 2 End-to-End TTS System
Authors:	Tihelka, Daniel Matoušek, Jindřich Tihelková, Alice
Citation:	TIHELKA, D. MATOUŠEK, J. TIHELKOVÁ, A. How Much End-to-End is Tacotron 2 End-to-End TTS System. In Text, Speech, and Dialogue 24th International Conference, TSD 2021, Olomouc, Czech Republic, September 6–9, 2021, Proceedings. Cham: Springer International Publishing, 2021. s. 511-522. ISBN: 978-3-030-83526-2 , ISSN: 0302-9743
Issue Date:	2021
Publisher:	Springer International Publishing
Document type:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85115273150 http://hdl.handle.net/11025/47247
ISBN:	978-3-030-83526-2
ISSN:	0302-9743
Keywords in different language:	End-to-end speech synthesis;Tacotron 2;WaveRNN;MelGan;Text processing;Homograph disambiguation;Prosody patterns
Abstract in different language:	In recent years, the concept of end-to-end text-to-speech synthesis has begun to attract the attention of researchers. The motivation is simple – replacing the individual modules that TTS traditionally built on with a powerful deep neural network simplifies the architecture of the entire system. However, how capable are such end-to-end systems of dealing with classic tasks such as G2P, text normalisation, homograph disambiguation and other issues inseparably linked to text-to-speech systems? In the present paper, we explore three free implementations of the Tacotron 2-based speech synthesizers, focusing on their abilities to transform the input text into correct pronunciation, not only in terms of G2P conversion but also in han- dling issues related to text analysis and the prosody patterns used.
Rights:	Plný text je přístupný v rámci univerzity přihlášeným uživatelům. © Springer
Appears in Collections:	Konferenční příspěvky / Conference papers (KAJ) Konferenční příspěvky / Conference Papers (KKY) OBD

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