Emotions as a component of prosody

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00162696" target="_blank" >RIV/68407700:21230/09:00162696 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Emotions as a component of prosody

Popis výsledku v původním jazyce

Prosody is one of the factors which make natural and synthetic speech sound differently. Apart from frequently used prosodic parameters, such as fundamental frequency, speech unit duration and intensity, other parameters related to prosody, for example voice timbre, are also studied. Timbre is related to the expression of emotions in speech, but can be impacted by pathological changes as well. The timbre, characteristic of each individual, is based on higher formant frequencies, which are a result of signal modification in vocal organs, reverberation in cranial cavity, but also lip and tongue position variations. A direct expression of emotions is problematic in Text-to-Speech (TTS) synthesis. Emotions are coded in speech signal only, not in text. Theycan serve as one of the input parameters for prosody modelling by artificial neural networks (ANN) in TTS synthesis. The prosody will not reflect any specific emotion, but will increase the naturalness of speech.

Název v anglickém jazyce

Emotions as a component of prosody

Popis výsledku anglicky

Prosody is one of the factors which make natural and synthetic speech sound differently. Apart from frequently used prosodic parameters, such as fundamental frequency, speech unit duration and intensity, other parameters related to prosody, for example voice timbre, are also studied. Timbre is related to the expression of emotions in speech, but can be impacted by pathological changes as well. The timbre, characteristic of each individual, is based on higher formant frequencies, which are a result of signal modification in vocal organs, reverberation in cranial cavity, but also lip and tongue position variations. A direct expression of emotions is problematic in Text-to-Speech (TTS) synthesis. Emotions are coded in speech signal only, not in text. Theycan serve as one of the input parameters for prosody modelling by artificial neural networks (ANN) in TTS synthesis. The prosody will not reflect any specific emotion, but will increase the naturalness of speech.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

<a href="/cs/project/GA102%2F09%2F0989" target="_blank" >GA102/09/0989: Nové perspektivní metody vysoce kvalitní syntézy mluvené češtiny</a><br>

Návaznosti

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

Rok uplatnění

2009

Kód důvěrnosti údajů

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

Název statě ve sborníku

Digital Technologies 2009

ISBN

978-80-554-0150-8

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

—

Název nakladatele

TU v Žilině

Místo vydání

Žilina

Místo konání akce

Žilina

Datum konání akce

12. 11. 2009

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—