Video-based Guided Source Separation
Shrishti S. Shetu, Soumitro Chakrabarty and Emanuel A. P. Habets
Publication: S. Shetu, S. Chakrabarty and E.A.P. Habets, "An empirical study of visual features for DNN based audio-visual speech enhancement in multi-talker environments,"" Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.
Pipeline
Demos
| mixture | separated | |
| 1 | ||
| 2 |