A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
Liu, David Harwath, Leonid Karlinsky, Hilde Kuehne, and James Glass
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
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.
- ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling