Layer-wise probing of wav2vec2-base and Whisper-small shows both models distinguish reduced vs. canonical consonant clusters in AAE with high accuracy and retain cues to underlying stops, encoding CCR as gradient variation.
Uncovering syllable constituents in the self-attention-based speech represen- tations of whisper,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SALSA adapts speech-aware LLMs via supervised layer-wise steering vectors, reporting up to 46.8% relative gains over zero-shot on out-of-domain speech benchmarks.
citing papers explorer
-
Layer-wise Probing of wav2vec 2.0 and Whisper for Consonant Cluster Reduction in African American English
Layer-wise probing of wav2vec2-base and Whisper-small shows both models distinguish reduced vs. canonical consonant clusters in AAE with high accuracy and retain cues to underlying stops, encoding CCR as gradient variation.
-
SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors
SALSA adapts speech-aware LLMs via supervised layer-wise steering vectors, reporting up to 46.8% relative gains over zero-shot on out-of-domain speech benchmarks.