Audio Source Separation
44 papers with code • 2 benchmarks • 14 datasets
Audio Source Separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals).
Source: Model selection for deep audio source separation via clustering analysis
Benchmarks
These leaderboards are used to track progress in Audio Source Separation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
AudioSet
WSJ0-2mix
MUSDB18
WHAM!
AVSpeech
Latest papers with no code
Sampling Frequency Independent Dialogue Separation
The models are trained with audio sampled at 8 kHz.
SepIt: Approaching a Single Channel Speech Separation Bound
We present an upper bound for the Single Channel Speech Separation task, which is based on an assumption regarding the nature of short segments of speech.
On loss functions and evaluation metrics for music source separation
We investigate which loss functions provide better separations via benchmarking an extensive set of those for music source separation.
Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds
A differentiable digital signal processing (DDSP) autoencoder is a musical sound synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis.
Fish sounds: towards the evaluation of marine acoustic biodiversity through data-driven audio source separation
Moreover, one of the causes of biodiversity loss is sound pollution; in data obtained from regions with loud anthropic noise, it is hard to separate the artificial from the fish sound manually.
Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning
In order to combat this problem, we present a new self-supervised learning pretext task for beat tracking and downbeat estimation.
Zero-shot Audio Source Separation through Query-based Learningfrom Weakly-labeled Data
Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training.
Reduction of Subjective Listening Effort for TV Broadcast Signals with Recurrent Neural Networks
Listening to the audio of TV broadcast signals can be challenging for hearing-impaired as well as normal-hearing listeners, especially when background sounds are prominent or too loud compared to the speech signal.
Visual Scene Graphs for Audio Source Separation
At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention.
Move2Hear: Active Audio-Visual Source Separation
We introduce the active audio-visual source separation problem, where an agent must move intelligently in order to better isolate the sounds coming from an object of interest in its environment.
