Skip to main content
. Author manuscript; available in PMC: 2014 Oct 7.
Published in final edited form as: Proc ACM Int Conf Multimodal Interact. 2012;2012:485–492. doi: 10.1145/2388676.2388781

Figure 1.

Figure 1

Comparison between the audio baseline and different acoustic and lexical features on the test set. Performance is measured in cross-correlation average over all sequences on the WLSC