DTM-Codec achieves better reconstruction quality and intelligibility than fixed-frame-rate neural speech codecs at matched total bitrate via dynamic token masking and Path Length Equalization for variable frame rates.
Learned token pruning for transformers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Token Merging (ToMe) doubles the throughput of large Vision Transformers on images, video, and audio by merging similar tokens with a fast matching algorithm, incurring only 0.2-0.4% accuracy loss.
citing papers explorer
-
DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection
DTM-Codec achieves better reconstruction quality and intelligibility than fixed-frame-rate neural speech codecs at matched total bitrate via dynamic token masking and Path Length Equalization for variable frame rates.
-
Token Merging: Your ViT But Faster
Token Merging (ToMe) doubles the throughput of large Vision Transformers on images, video, and audio by merging similar tokens with a fast matching algorithm, incurring only 0.2-0.4% accuracy loss.