WaveNet-Based Speech Synthesis Applied to Czech - A Comparison with the Traditional Synthesis Methods

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952601" target="_blank" >RIV/49777513:23520/18:43952601 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-030-00794-2_48" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-030-00794-2_48</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-00794-2_48" target="_blank" >10.1007/978-3-030-00794-2_48</a>

Jazyk výsledku

angličtina

Název v původním jazyce

WaveNet-Based Speech Synthesis Applied to Czech - A Comparison with the Traditional Synthesis Methods

Popis výsledku v původním jazyce

WaveNet is a recently-developed deep neural network for generating high-quality synthetic speech. It produces directly raw audio samples. This paper describes the first application of WaveNet-based speech synthesis for the Czech language. We used the basic WaveNet architecture. The duration of particular phones and the required fundamental frequency used for local conditioning were estimated by additional LSTM networks. We conducted a MUSHRA listening test to compare WaveNet with 2 traditional synthesis methods: unit selection and HMM-based synthesis. Experiments were performed on 4 large speech corpora. Though our implementation of WaveNet did not outperform the unit selection method as reported in other studies, there is still a lot of scope for improvement, while the unit selection TTS have probably reached its quality limit.

Název v anglickém jazyce

WaveNet-Based Speech Synthesis Applied to Czech - A Comparison with the Traditional Synthesis Methods

Popis výsledku anglicky

WaveNet is a recently-developed deep neural network for generating high-quality synthetic speech. It produces directly raw audio samples. This paper describes the first application of WaveNet-based speech synthesis for the Czech language. We used the basic WaveNet architecture. The duration of particular phones and the required fundamental frequency used for local conditioning were estimated by additional LSTM networks. We conducted a MUSHRA listening test to compare WaveNet with 2 traditional synthesis methods: unit selection and HMM-based synthesis. Experiments were performed on 4 large speech corpora. Though our implementation of WaveNet did not outperform the unit selection method as reported in other studies, there is still a lot of scope for improvement, while the unit selection TTS have probably reached its quality limit.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/GA16-04420S" target="_blank" >GA16-04420S: Kombinované využití fonetických a korpusově založených postupů při odstraňování rušivých jevů v řečové syntéze</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Text, Speech, and Dialogue 21st International Conference, TSD 2018, Brno, Czech Republic, September 11-14, 2018, Proceedings

ISBN

978-3-030-00793-5

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

8

Strana od-do

445-452

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Cham

Místo konání akce

Brno, Czech Republic

Datum konání akce

11. 9. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—