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.
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...
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:2610.08604v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) systems often show uneven performance across demographic groups, and errors can be especially difficult to address f...
arXiv:2607. 09891v1 Announce Type: cross Abstract: Audio deepfake detection models determine whether speech is genuine or artificially generated, but high overall accuracy can mask substantial performance disparities across demographic groups.
Automatic Speech Recognition (ASR) systems often show uneven performance across demographic groups, and errors can be especially difficult to address for speakers belonging to multiple demographic gro...
arXiv:2608. 19936v1 Announce Type: cross Abstract: Public benchmarks are important measures of Automatic Speech Recognition (ASR) model capabilities.
arXiv:2606. 19823v1 Announce Type: cross Abstract: Automatic speech recognition remains unreliable for dysarthric speech due to data scarcity and high inter-speaker variability.
arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.
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.
Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data. We propose an augmentation pipeline that generates scenario-level dialogues with participant metadata, maps speaker attributes to TTS voice profiles, and assembles synthesized utterances into speaker-aware simulated conversations.
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.
arXiv:2607. 14753v1 Announce Type: cross Abstract: Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker verification (ASV).