Title: Czech Speech Synthesis with Generative Neural Vocoder
Authors: Vít, Jakub
Hanzlíček, Zdeněk
Matoušek, Jindřich
Citation: VÍT, J., HANZLÍČEK, Z., MATOUŠEK, J. Czech Speech Synthesis with Generative Neural Vocoder. In: Text, Speech, and Dialogue 22nd International Conference, TSD 2019, Ljubljana,Slovenia, September 11-13, 2019, Proceedings. Cham: Springer, 2019. s. 307-315. ISBN 978-3-030-27946-2 , ISSN 0302-9743.
Issue Date: 2019
Publisher: Springer
Document type: konferenční příspěvek
URI: 2-s2.0-85072849542
ISBN: 978-3-030-27946-2
ISSN: 0302-9743
Keywords in different language: Speech synthesis, LSTM-based speech synthesis, WaveRNN, Neural vocoder, Unit selection
Abstract: In recent years, new neural architectures for generating high-quality synthetic speech on a per-sample basis were introduced. We describe our application of statistical parametric speech synthesis based on LSTM neural networks combined with a generative neural vocoder for the Czech language. We used a traditional LSTM architecture for generating vocoder parametrization from linguistic features. We replaced a standard vocoder with a WaveRNN neural network. We conducted a MUSHRA listening test to compare the proposed approach with the unit selection and LSTM-based parametric speech synthesis utilizing a standard vocoder. In contrast with our previous work, we managed to outperform a well-tuned unit selection TTS system by a great margin on both professional and amateur voices.
Rights: Plný text není přístupný.
© Springer
Appears in Collections:Konferenční příspěvky / Conference papers (NTIS)
Konferenční příspěvky / Conference Papers (KKY)

Files in This Item:
File SizeFormat 
Vit2019_Chapter_CzechSpeechSynthesisWithGenera.pdf401,08 kBAdobe PDFView/Open    Request a copy

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/36715

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

  1. DSpace at University of West Bohemia
  2. Publikační činnost / Publications
  3. OBD