Yixuan He
Author directory2026
TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition
Xinyu Wang | Ziyu Zhao | Ke Bai | Silin Meng | Dongming Shen | Xiao-Wen Chang | Yixuan He
Findings of the Association for Computational Linguistics: EMNLP 2026
Xinyu Wang | Ziyu Zhao | Ke Bai | Silin Meng | Dongming Shen | Xiao-Wen Chang | Yixuan He
Findings of the Association for Computational Linguistics: EMNLP 2026
Data-aware post-training quantization (PTQ) minimizes a per-token reconstruction loss on a small calibration corpus—an objective natural for average-token preservation, but one that implicitly weights positions by their empirical frequency. For **Automatic Speech Recognition (ASR)**, this weighting is misaligned with tail-sensitive recognition risk: names, numerals, technical terms, and domain-specific words are practically important but receive proportionally little calibration mass.
We propose **Tail-Aware Reconstruction Quantization (TARQ)**, a label-free PTQ framework that shifts calibration toward the lexical tail. **TARQ** introduces **rareBAL**, a closed-form per-Linear-layer rule that equalizes the calibration mass contributed by common and tail positions, plus a metric-consistent residual correction that aligns the sequential PTQ sweep with the reweighted objective. **TARQ** requires no entity labels, no curated calibration set, no validation decoding, and no additional training.
Across eight ASR backbones and eight datasets under 4-bit weight-only quantization, **TARQ** improves mean rare-WER, the **Word Error Rate (WER)** restricted to rare-word reference positions, while maintaining competitive aggregate WER. It achieves the lowest cross-corpus rare-WER swing, **0.63 percentage points (pp)**, among compared methods, and transfers without modification to entity-rich evaluation on ProfASR and ContextASR-Speech-En with no entity supervision.
We propose **Tail-Aware Reconstruction Quantization (TARQ)**, a label-free PTQ framework that shifts calibration toward the lexical tail. **TARQ** introduces **rareBAL**, a closed-form per-Linear-layer rule that equalizes the calibration mass contributed by common and tail positions, plus a metric-consistent residual correction that aligns the sequential PTQ sweep with the reweighted objective. **TARQ** requires no entity labels, no curated calibration set, no validation decoding, and no additional training.
Across eight ASR backbones and eight datasets under 4-bit weight-only quantization, **TARQ** improves mean rare-WER, the **Word Error Rate (WER)** restricted to rare-word reference positions, while maintaining competitive aggregate WER. It achieves the lowest cross-corpus rare-WER swing, **0.63 percentage points (pp)**, among compared methods, and transfers without modification to entity-rich evaluation on ProfASR and ContextASR-Speech-En with no entity supervision.