Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
1
0
A novel reference-free metric objectively quantifies audio-visual complexity in virtual environments, decoupling modality-specific contributions and revealing their independent dynamics.
XSQ-AST is presented, a framework that combines the SQ-AST speech quality model with WhisperX phoneme alignment and multiple saliency methods to produce temporally localised artifact diagnostics without model retraining.