Abstract: The quality evaluation of audio-visual (A/V) content has become increasingly critical in modern multimedia communication systems. Traditional single-modality quality evaluation methods and ...
Abstract: Prior research on directional focus decoding, a.k.a. selective Auditory Attention Decoding (sAAD), has primarily focused on binary “left-right” tasks. However, decoding of the attended ...
Experimental Extension Fork Based on whisper-vits-svc, this fork introduces modifications to explicitly re-inject singing expressions (dynamics, breathiness, vocal push, and vocal core) into the model ...