#whisper-asr News & Analysis

4 articles tagged with #whisper-asr. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · Jun 87/10

🧠

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

Researchers demonstrate that Whisper, OpenAI's widely-used speech recognition model, can detect and mitigate hallucinations—fabricated coherent transcriptions from non-speech audio—using Sparse AutoEncoders and activation-space steering. The approach reduces hallucination rates from 72-87% to 14-27% across model sizes with minimal performance degradation on actual speech.

AIBearisharXiv – CS AI · Apr 137/10

🧠

From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales

Researchers propose the Spectral Sensitivity Theorem to explain hallucinations in large ASR models like Whisper, identifying a phase transition between dispersive and attractor regimes. Analysis of model eigenspectra reveals that intermediate models experience structural breakdown while large models compress information, decoupling from acoustic evidence and increasing hallucination risk.

AINeutralarXiv – CS AI · Jun 236/10

🧠

From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection

Researchers developed multiple approaches to detect hallucinations in OpenAI's Whisper ASR model, where the system generates fluent but unfounded transcriptions. The study found that probing the model's internal decoder states outperformed text-based and LLM-based detection methods, with a hybrid approach combining text metrics and internal representations achieving the best overall performance.

AINeutralarXiv – CS AI · May 126/10

🧠

Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models

Researchers present a unified mathematical framework for Test-Time Adaptation (TTA) in autoregressive generative models, decomposing entropy minimization into token-level policy gradient and entropy losses. Validated on Whisper ASR across 20+ domains, the approach demonstrates consistent performance improvements and reconciles previously disparate adaptation methods under a single theoretical foundation.