Single-Label Target Sound Extraction
0 benchmarks • 0 datasets
Single-Label Target Sound Extraction is the task of extracting a given class of sounds from an audio mixture. The audio mixture may contain background noise with a relatively low amplitude compared to the foreground mixture components. The choice of the sound class is provided as input to the model in form of a string, integer, or a one-hot encoding of the sound class.
Benchmarks
These leaderboards are used to track progress in Single-Label Target Sound Extraction
No evaluation results yet. Help compare methods by
submitting
evaluation metrics.