Study on Audio-Visual Asynchrony of Russian Speech for Improvement of Talking Head Naturalness

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F09%3A00502847" target="_blank" >RIV/49777513:23520/09:00502847 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Study on Audio-Visual Asynchrony of Russian Speech for Improvement of Talking Head Naturalness

Popis výsledku v původním jazyce

An audio-visual speech synthesis system with modeling of asynchrony between auditory and visual speech streams has been proposed in the paper. Corpus-based study of real multimedia recordings gave us the required data for understanding the problem of modalities asynchrony that is partially caused by the co-articulation phenomena. A set of context-dependent timing rules and recommendations was elaborated in order to make a synchronization of auditory and visual speech cues of the animated talking head similar to a natural humanlike way. The proposed asynchrony model was introduced into the audio-driven talking head as an intermediate level for visual synthesis controlling. The cognitive evaluation of the model-based Russian-speaking talking head with implementation of the original asynchrony model has shown high intelligibility and naturalness of audio-visual synthesized speech.

Název v anglickém jazyce

Study on Audio-Visual Asynchrony of Russian Speech for Improvement of Talking Head Naturalness

Popis výsledku anglicky

An audio-visual speech synthesis system with modeling of asynchrony between auditory and visual speech streams has been proposed in the paper. Corpus-based study of real multimedia recordings gave us the required data for understanding the problem of modalities asynchrony that is partially caused by the co-articulation phenomena. A set of context-dependent timing rules and recommendations was elaborated in order to make a synchronization of auditory and visual speech cues of the animated talking head similar to a natural humanlike way. The proposed asynchrony model was introduced into the audio-driven talking head as an intermediate level for visual synthesis controlling. The cognitive evaluation of the model-based Russian-speaking talking head with implementation of the original asynchrony model has shown high intelligibility and naturalness of audio-visual synthesized speech.

Druh

O - Ostatní výsledky

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

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