Introduces a conceptual framework for curiosity-driven reward-based learning in audio via continuous search for novel sound sources, with an overview of prior work and a proof-of-concept.
Computer audition: From task-specific machine learning to foundation models,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Larger pre-training data scale and class diversity improve audio transfer learning performance, yet similarity between pre-training and target task has a stronger positive effect.
citing papers explorer
-
A conceptual framework for learning to listen by reward: Curiosity-driven search for novel sources
Introduces a conceptual framework for curiosity-driven reward-based learning in audio via continuous search for novel sound sources, with an overview of prior work and a proof-of-concept.
-
How Class Ontology and Data Scale Affect Audio Transfer Learning
Larger pre-training data scale and class diversity improve audio transfer learning performance, yet similarity between pre-training and target task has a stronger positive effect.