TARQ applies a closed-form per-layer rule called rareBAL to equalize calibration mass between common and tail words in ASR quantization, improving rare-WER across models and datasets without aggregate WER regression.
headies are all over the place
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition
TARQ applies a closed-form per-layer rule called rareBAL to equalize calibration mass between common and tail words in ASR quantization, improving rare-WER across models and datasets without aggregate WER regression.