Real-Time Speech Driven Gesture Animation

被引：0

作者：

Kasarci, Kenan ^{[1
]}

Bozkurt, Elif ^{[1
]}

Yemez, Yucel ^{[1
]}

Erzin, Engin ^{[1
]}

机构：

[1] Koc Univ, Multimedya Goru & Graf Lab, Istanbul, Turkey

来源：

2016 24TH SIGNAL PROCESSING AND COMMUNICATION APPLICATION CONFERENCE (SIU) | 2016年

关键词：

Viterbi; speech driven gesticulation; realtime; animation;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Gesture and speech co-exist in time with a tight synchrony, and they are planned and shaped by the emotional state and produced together. In our early studies we have developed joint gesture-speech models and proposed algorithms for speech driven gesture animation. These algorithms mainly based on the Viterbi decoders and can not run in realtime. In this paper we are presenting necessary modifications of these algorithms to run in realtime. In the experimental studies we present the conditions that satisfy realtime factor of 1. We as well demonstrate the realtime and non-realtime speech driven gesture animations for subjective evaluations.

引用

页码：1917 / 1920

页数：4

共 15 条

[1]

[Anonymous], 2010, ACM T GRAPHICS SIGGR

[2]

Beskow J., 2003, TALKING HEADS MODELS

[3]

Bozkurt E, 2013, INT CONF ACOUST SPEE, P3652, DOI 10.1109/ICASSP.2013.6638339

[4]

Brand M, 1999, COMP GRAPH, P21, DOI 10.1145/311535.311537

[5]

Bregler C., 1997, Computer Graphics Proceedings, SIGGRAPH 97, P353, DOI 10.1145/258734.258880

[6]

Cassell J, 2000, EMBODIED CONVERSATIONAL AGENTS, P1

[7]

David McNeill., 1992, HAND MIND WHAT GESTU

[8]

Ezzat Tony., 2002, Trainable videorealistic speech animation, V21

[9]

Kasarci K., 2016, GERCEK ZAMANLI KONUS

[10]

Kendon A., 1980, The Relationship of Verbal and Nonverbal Communication, Mouton, P207, DOI 10.1515/9783110813098.207

← 1 2 →