Skip to main content
Advertisement

< Back to Article

Modulation transfer functions for audiovisual speech

Fig 4

CCA results for the GRID dataset.

CCA-derived envelope filters (left) and corresponding face loadings (right) for the GRID dataset. Unlike in the wild recordings of natural speech such as the LRS3, the GRID corpus is composed of simple, syntactically identical six-word sentences.

Fig 4

doi: https://doi.org/10.1371/journal.pcbi.1010273.g004