The group focuses on measurement and evaluation methods to facilitate the use of technologies that provide easier access to multimedia and multi-lingual information and that improve human-computer interface modalities. These technologies include recognizing and/or transforming information in speech, text, images, video, and other multimedia modalities, and the fusion of heterogeneous media content. Focus areas include speech recognition, speaker recognition, language recognition, machine translation, image processing, image understanding, video processing, visual recognition, 2-D and 3D shape analysis, image quality assessment, and interoperable digital media access.