Target Sound Extraction
4 papers with code • 3 benchmarks • 3 datasets
Target Sound Extraction is the task of extracting a sound corresponding to a given class 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 Target Sound Extraction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
AudioSet
AudioCaps
FSDSoundScapes
Most implemented papers
Real-Time Target Sound Extraction
vb000/waveformer
•
•
We present the first neural network model to achieve real-time and streaming target sound extraction.
Target Sound Extraction with Variable Cross-modality Clues
lichenda/multi-clue-tse-data
•
•
Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources.
DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction
JHU-LCAP/DPM-TSE
•
•
Common target sound extraction (TSE) approaches primarily relied on discriminative approaches in order to separate the target sound while minimizing interference from the unwanted sources, with varying success in separating the target from the background.
CLAPSep: Leveraging Contrastive Pre-trained Models for Multi-Modal Query-Conditioned Target Sound Extraction
Such systems consist of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound based on conditional embeddings.
