The paper investigates how post‑training compression techniques—such as pruning, quantization, and distillation—affect demographic fairness in Whisper speech‑recognition models. It finds that pruning and INT4 quantization significantly widen word‑error‑rate gaps between demographic groups, especially for Black/AA and Asian speakers, while distillation tends to reduce these gaps. The study introduces a temporal‑taxation metric to quantify the increased correction effort required for marginalized speakers after compression.
arXiv:2609.18533v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representation...
arXiv:2609.38106v1 Announce Type: cross Abstract: Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggre...
Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representations. We ask whether speaker-linked attributes that...
The paper presents a new evaluation protocol for post‑training quantization of speech language models that separates lexical output, transcript‑insufficient endpoints, and packed implementations. In a Qwen2‑Audio case study, a 6‑bit allocation selected for translation improves chrF scores but degrades emotion recognition, while uniform and front‑layer controls perform better on emotion tasks. Similar patterns hold at 7 bits, and a 4‑bit study shows consistent emotion deficits across all low‑bit allocations, with no advantage for the selected scheme. The study highlights a precision‑dependent mismatch between lexical output, waveform‑dependent behavior, and nominal precision, without claiming a general failure of low‑bit models or a deployment benefit for the selected allocation.
arXiv:2606. 24083v1 Announce Type: cross Abstract: "Talk short.
The paper introduces AWED, a word‑level emission‑delay metric, and demonstrates that post‑training a delayed‑streaming model with a joint reward (GRPO) improves both accuracy and latency. Using a single operating point (τ=6 frames), the method outperforms both its supervised baseline and the Voxtral Realtime backbone across all lookahead budgets, reducing WER by up to 30.8% at 80 ms delay and lowering median AWED from 1.17 s to 1.04 s.
The paper presents an interpretable, fair, and accurately benchmarked automated system for assessing second‑language English speaking. Using a hybrid of feature‑based speech‑timing metrics and a large language model (LLM) fluency judgment, the system achieves a Spearman correlation of 0.818 with the ICNALE Global Rating Archive, outperforming 81 % of trained human raters. A controlled study shows that encoding pauses into the LLM prompt does not meaningfully affect fluency scores, indicating that the system’s fluency signal derives from measurable speech‑timing features.
arXiv:2606. 07608v1 Announce Type: cross Abstract: We present a systematic study of fine-tuning OpenAI's Whisper large-v3 for Swiss German ASR, using 1,367 hours of broadcast speech paired with Standard German subtitles as weak supervision.
arXiv:2606. 01016v1 Announce Type: cross Abstract: While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription.
arXiv:2508. 07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length.
arXiv:2606. 22790v2 Announce Type: replace-cross Abstract: In this paper, we investigate the tradeoffs between compute allocation and model performance for two speech processing tasks: Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER).
X-AuT is a progressive framework for compressing the audio encoder of speech large language models. It selects layer combinations via short behavioral probes and restores performance through representation alignment, cross‑scale distillation, scheduled student‑policy supervision, and LoRA finetuning, while keeping the language‑model backbone frozen. On ten Chinese–English benchmarks, reducing Qwen3‑ASR‑0.6B’s encoder from 18 to 16 layers lowers macro‑average error from 5.61% to 5.27%, and a 14‑layer model achieves 5.75% error with 20.7% fewer parameters.