Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data. (arXiv:2112.07891v3 [cs.SD] UPDATED)

Deep learning techniques for separating audio into different sound sources
face several challenges. Standard architectures require training separate
models for different types of audio sources. Although some universal separators
employ a single model to target multiple sources, they have difficulty
generalizing to unseen sources. In this paper, we propose a three-component
pipeline to train a universal audio source separator from a large, but
weakly-labeled dataset: AudioSet. First, we propose a transformer-based sound
event detection system for processing weakly-labeled training data. …

arxiv audio data learning