Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices

Niels Egberts
Niels Egberts
Fergus Henderson
Fergus Henderson
Przemyslaw Szczepaniak
Przemyslaw Szczepaniak

INTERSPEECH, pp. 2273-2277, 2016.

Cited by: 76|Bibtex|Views33|DOI:https://doi.org/10.21437/Interspeech.2016-522
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Acoustic models based on long short-term memory recurrent neural networks (LSTM-RNNs) were applied to statistical parametric speech synthesis (SPSS) and showed significant improvements in naturalness and latency over those based on hidden Markov models (HMMs). This paper describes further optimizations of LSTM-RNN-based SPSS for deploymen...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments