Avoiding Model Complexity in Limited Domain Speech Synthesis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43926595" target="_blank" >RIV/49777513:23520/15:43926595 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Avoiding Model Complexity in Limited Domain Speech Synthesis

Popis výsledku v původním jazyce

Nowadays, text-to-speech (TTS) synthesis, an artificial speech creation, appears in many areas, but it is still always recognizable from real human speech and so its perception can be sometimes negative. To ensure a higher quality of speech synthesis, the TTS system should deal with the complexity of speech, which is very difficult (in fact, coping with all the complexity is probably impossible). But there are some areas of applications in which the complexity is already implicitly contained in the textand speech corresponding to it, and, if the TTS is properly designed, we do not have to deal with that. The purpose of this chapter is therefore to describe how to built such a system, to discuss the limitations/restrictions on that and to compare its quality to the quality of general TTS system.

Název v anglickém jazyce

Avoiding Model Complexity in Limited Domain Speech Synthesis

Popis výsledku anglicky

Nowadays, text-to-speech (TTS) synthesis, an artificial speech creation, appears in many areas, but it is still always recognizable from real human speech and so its perception can be sometimes negative. To ensure a higher quality of speech synthesis, the TTS system should deal with the complexity of speech, which is very difficult (in fact, coping with all the complexity is probably impossible). But there are some areas of applications in which the complexity is already implicitly contained in the textand speech corresponding to it, and, if the TTS is properly designed, we do not have to deal with that. The purpose of this chapter is therefore to describe how to built such a system, to discuss the limitations/restrictions on that and to compare its quality to the quality of general TTS system.

Druh

C - Kapitola v odborné knize

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/ED1.1.00%2F02.0090" target="_blank" >ED1.1.00/02.0090: NTIS - Nové technologie pro informační společnost</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název knihy nebo sborníku

Tackling the Complexity in Speech

ISBN

978-80-7308-558-2

Počet stran výsledku

12

Strana od-do

183-194

Počet stran knihy

230

Název nakladatele

Univerzita Karlova v Praze

Místo vydání

Praha

Kód UT WoS kapitoly

—