Near-videorealistic synthetic visual speech using non-rigid appearance models

Autor:	Gavin C. Cawley, J.A. Bangham, Barry-John Theobald, I.A. Matthews
Rok vydání:	2004
Předmět:	Computer science Speech recognition Face (geometry) Speech synthesis Concatenative synthesis Speech processing Face detection computer.software_genre Hidden Markov model computer Computer facial animation Computer animation
Zdroj:	ICASSP (5)
DOI:	10.1109/icassp.2003.1200092
Popis:	We present work towards videorealistic synthetic visual speech using non-rigid appearance models. These models are used to track a talking face enunciating a set of training sentences. The resultant parameter trajectories are used in a concatenative synthesis scheme, where samples of original data are extracted from a corpus and concatenated to form new unseen sequences. Here we explore the effect on the synthesiser output of blending several synthesis units considered similar to the desired unit. We present preliminary subjective and objective results used to judge the realism of the system.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::2562eb6299ada5d4586a0c39e4d0c363 https://doi.org/10.1109/icassp.2003.1200092 Zobrazit plný text záznamu