Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
SDR – Half-baked or Well Done?
TLDR
It is argued here that the signal-to-distortion ratio (SDR) implemented in the BSS_eval toolkit has generally been improperly used and abused, especially in the case of single-channel separation, resulting in misleading results.
View on IEEE
Full-Capacity Unitary Recurrent Neural Networks
TLDR
This work provides a theoretical argument to determine if a unitary parameterization has restricted capacity, and shows how a complete, full-capacity unitary recurrence matrix can be optimized over the differentiable manifold of unitary matrices.
View PDF on arXiv
Universal Sound Separation
TLDR
A dataset of mixtures containing arbitrary sounds is developed, and the best methods produce an improvement in scale-invariant signal-to-distortion ratio of over 13 dB for speech/non-speech separation and close to 10 dB for universal sound separation.
View on IEEE
Enabling Seamless Wireless Power Delivery in Dynamic Environments
TLDR
An overview of methods used to adapt to variations in range, orientation, and load using both wideband and fixed-frequency techniques is provided.
View on IEEE
Unsupervised Sound Separation Using Mixture Invariant Training
TLDR
This paper proposes a completely unsupervised method, mixture invariant training (MixIT), that requires only single-channel acoustic mixtures and shows that MixIT can achieve competitive performance compared to supervised methods on speech separation.
View Paper
Building recurrent networks by unfolding iterative thresholding for sequential sparse recovery
TLDR
This paper shows that the iterative soft-thresholding algorithm (ISTA) for sequential sparse recovery corresponds to a stacked recurrent neural network (RNN) under specific architecture and parameter constraints.
View on IEEE
Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery
TLDR
The weights of the SISTA-RNN are perfectly interpretable as the parameters of a principled statistical model, which in this case include a sparsifying dictionary, iterative step size, and regularization parameters, which results in a novel stacked RNN architecture.
View PDF on arXiv
Unsupervised Sound Separation Using Mixtures of Mixtures
TLDR
This paper proposes a completely unsupervised method, mixture invariant training (MixIT), that requires only single-channel acoustic mixtures and shows that MixIT can achieve competitive performance compared to supervised methods on speech separation.
View PDF on arXiv
What’s all the Fuss about Free Universal Sound Separation Data?
TLDR
An open-source baseline separation model that can separate a variable number of sources in a mixture is introduced, based on an improved time-domain convolutional network (TDCN++), that achieves scale-invariant signal-to-noise ratio improvement (SI-SNRi) on mixtures with two to four sources.
View on IEEE
Differentiable Consistency Constraints for Improved Deep Speech Enhancement
TLDR
This paper presents a new approach to masking that applies mixture consistency to complex-valued short-time Fourier transforms (STFTs) using real-valued masks, and shows that this approach can be effective in speech enhancement.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License