Derives a rigorous entropy minimization formulation for autoregressive test-time adaptation that decomposes into policy gradient and entropy terms, reinterpreting prior methods and improving Whisper ASR across 20+ domains.
wav2vec 2.0: A framework for self-supervised learning of speech representa- tions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
eess.AS 2years
2026 2verdicts
UNVERDICTED 2roles
dataset 1polarities
use dataset 1representative citing papers
Emotion embedding similarities are unsuitable for zero-shot evaluation of emotional expressiveness in speech generation due to confounding by non-emotional acoustic features.
citing papers explorer
-
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
Derives a rigorous entropy minimization formulation for autoregressive test-time adaptation that decomposes into policy gradient and entropy terms, reinterpreting prior methods and improving Whisper ASR across 20+ domains.
-
The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation
Emotion embedding similarities are unsuitable for zero-shot evaluation of emotional expressiveness in speech generation due to confounding by non-emotional acoustic features.