AcuLa aligns audio models with medical language models via contrastive and self-supervised objectives on LLM-generated clinical reports, raising mean AUROC from 0.68 to 0.79 across 18 cardio-respiratory tasks.
Audioclip: Extending clip to image, text and audio
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
citing papers explorer
-
Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding
AcuLa aligns audio models with medical language models via contrastive and self-supervised objectives on LLM-generated clinical reports, raising mean AUROC from 0.68 to 0.79 across 18 cardio-respiratory tasks.
-
From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.