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...
arXiv:2609.27382v1 Announce Type: cross Abstract: Speech technology penalizes some voices: recognition errs nearly twice as often for Black speakers, and accuracy declines for second-language accents...
arXiv:2609.38976v1 Announce Type: new Abstract: Demographic fairness gaps in automatic speech recognition are almost always reported from a single training run. We fine-tune the Q-former projector an...
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.
Speech technology penalizes some voices: recognition errs nearly twice as often for Black speakers, and accuracy declines for second-language accents and older speakers. We introduce TRIAD, an audit g...
arXiv:2609.36500v1 Announce Type: cross Abstract: Speaker verification systems encounter combinations of noise, channel distortion, and changes in speech. Evaluating each condition separately does no...
The paper introduces asymmetric classifier‑free guidance (CFG) for target‑speaker ASR using Whisper, where a speaker‑conditioned branch predicts the target transcript and a speaker‑unconditioned branch predicts serialized multi‑speaker transcripts. CFG modulates the influence of speaker conditioning during decoding via a single guidance scale, which is first set globally on development data and then refined per utterance by a lightweight encoder‑based predictor while keeping the recognition model fixed. The resulting system yields up to 21.8% relative WER reduction over a condition‑only baseline and 5.6% over standard conditional decoding under domain shifts.
The paper explores activation steering as a method to enhance automatic speech recognition (ASR) performance and demographic fairness. It compares two techniques—paired activation subtraction and supervised optimization—finding that supervised optimization effectively improves overall ASR accuracy and fairness across gender, age, and dialect. The study also demonstrates that steering vectors trained on acoustically similar speakers can yield competitive or superior results, enabling few‑shot or zero‑shot adaptation without requiring demographic labels.
AfriBED is a newly released speech recognition bias evaluation dataset focused on two low‑resource African languages, Bemba and Nyanja. It contains 9 hours of Bemba speech from 80 speakers (3,928 utterances) and about 18 hours of Nyanja speech from 127 speakers (6,260 utterances). Baseline experiments show the data can be used to detect and quantify gender and speaker‑type bias in ASR systems for these languages.
Despite advancements in automatic speech recognition systems (ASR), current systems exhibit speaker-attribute bias, i.e., their speech recognition performance is biased against certain speakers based...
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...
arXiv:2601.09050v2 Announce Type: replace Abstract: Tonal low-resource languages are widely spoken but remain underserved by modern speech technologies. A central challenge is learning speech represe...