作者: Tsuhan Chen , R.R. Rao
DOI: 10.1109/5.664274
关键词:
摘要: We review recent research that examines audio-visual integration in multimodal communication. The topics include bimodality human speech, and automated lip reading, facial animation, synchronization, joint audio-video coding, bimodal speaker verification. also study the enabling technologies for these topics, including automatic facial-feature tracking audio-to-visual mapping. Recent progress shows processing of audio video provides advantages are not available when processed independently.