Adaptive saliency-guided supervoxel tokenization cuts 3D AR token length to 12.8% of uniform voxels while claiming SOTA quality and ~10× speedup on Trellis-500K.
Coding speech through vocal tract kinematics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
SPARC articulatory features predict sEMG signals more accurately than phoneme features across aloud, mimed, and subvocal speech, with consistent anatomical patterns and above-chance performance even in silent mode.
citing papers explorer
-
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
Adaptive saliency-guided supervoxel tokenization cuts 3D AR token length to 12.8% of uniform voxels while claiming SOTA quality and ~10× speedup on Trellis-500K.
-
Comparison of sEMG Encoding Accuracy Across Speech Modes Using Articulatory and Phoneme Features
SPARC articulatory features predict sEMG signals more accurately than phoneme features across aloud, mimed, and subvocal speech, with consistent anatomical patterns and above-chance performance even in silent mode.