arXiv (All)
open access
A Probe Shift Is Not a Fairness Fix: The Limits of Representation Steering in Speech Models
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 are linearly readable from pretrained ASR encoders yield useful directions for reducing group word-e
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability#1048488
- Like humans, language models demonstrate face-to-character biases.#469009
- Context-dependent acoustic dimensions underlying voice discrimination: Evidence from interpretable machine learning modeling of human perception#626479
- Context-dependent acoustic dimensions underlying voice discrimination: Evidence from interpretable machine learning modeling of human perception#171058
- Synthetic Speech Attribution via Prototypical Networks#1144889
Record · ID 1012713
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive