Search Results for author:
Found 45 papers, 25 papers with code
Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations
Non-negative Matrix Factorization (NMF) is a powerful technique for analyzing regularly-sampled data, i. e., data that can be stored in a matrix.
Sound Source Separation Using Latent Variational Block-Wise Disentanglement
In this paper, we present a hybrid classical digital signal processing/deep neural network (DSP/DNN) approach to source separation (SS) highlighting the theoretical link between variational autoencoder and classical approaches to SS.
Audio Editing with Non-Rigid Text Prompts
We show that the proposed editing pipeline is able to create audio edits that remain faithful to the input audio.
Mechatronic Generation of Datasets for Acoustics Research
We address the challenge of making spatial audio datasets by proposing a shared mechanized recording space that can run custom acoustic experiments: a Mechatronic Acoustic Research System (MARS).
Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Pitch estimation is an essential step of many speech processing algorithms, including speech coding, synthesis, and enhancement.
Complete and separate: Conditional separation with missing target source attribute completion
Recent approaches in source separation leverage semantic information about their input mixtures and constituent sources that when used in conditional separation models can achieve impressive performance.
Unsupervised Improvement of Audio-Text Cross-Modal Representations
In this paper, we study unsupervised approaches to improve the learning framework of such representations with unpaired text and audio.
A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement.
Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models.
Latent Iterative Refinement for Modular Source Separation
During inference, we can dynamically adjust how many processing blocks and iterations of a specific block an input signal needs using a gating module.
Optimal Condition Training for Target Source Separation
Recent research has shown remarkable performance in leveraging multiple extraneous conditional and non-mutually exclusive semantic concepts for sound source separation, allowing the flexibility to extract a given target source based on multiple different queries.
Semi-supervised Time Domain Target Speaker Extraction with Attention
In this work, we propose Exformer, a time-domain architecture for target speaker extraction.
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
In this paper, we work on a sound recognition system that continually incorporates new sound classes.
Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
As deep speech enhancement algorithms have recently demonstrated capabilities greatly surpassing their traditional counterparts for suppressing noise, reverberation and echo, attention is turning to the problem of packet loss concealment (PLC).
Heterogeneous Target Speech Separation
We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e. g., loudness, gender, language, spatial location, etc).
End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation
Neural vocoders have recently demonstrated high quality speech synthesis, but typically require a high computational complexity.
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so.
RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
RemixIT is based on a continuous self-training scheme in which a pre-trained teacher model on out-of-domain data infers estimated pseudo-target signals for in-domain mixtures.
Differentiable Signal Processing With Black-Box Audio Effects
We present a data-driven approach to automate audio signal processing by incorporating stateful third-party, audio effects as layers within a deep neural network.
Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data
We propose FEDENHANCE, an unsupervised federated learning (FL) approach for speech enhancement and separation with non-IID distributed data across multiple clients.
Point Cloud Audio Processing
As a consequence, most audio machine learning models are designed to process fixed-size vector inputs which often prohibits the repurposing of learned models on audio with different sampling rates or alternative representations.
Compute and memory efficient universal sound source separation
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem.
Ranked #4 on
Speech Separation
on WHAMR!
Optimizing Short-Time Fourier Transform Parameters via Gradient Descent
The Short-Time Fourier Transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks.
Unified Gradient Reweighting for Model Biasing with Applications to Source Separation
In this paper, we propose a simple, unified gradient reweighting scheme, with a lightweight modification to bias the learning process of a model and steer it towards a certain distribution of results.
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
In this paper, we present an efficient neural network for end-to-end general purpose audio source separation.
Ranked #10 on
Speech Separation
on WHAMR!
Self-supervised Learning for Speech Enhancement
Supervised learning for single-channel speech enhancement requires carefully labeled training examples where the noisy mixture is input into the network and the network is trained to produce an output close to the ideal target.
Audio and Speech Processing Sound
Two-Step Sound Source Separation: Training on Learned Latent Targets
In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is optimal.
Ranked #25 on
Speech Separation
on WSJ0-2mix
Continual Learning of New Sound Classes using Generative Replay
We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data.
Deep Tensor Factorization for Spatially-Aware Scene Decomposition
We propose a completely unsupervised method to understand audio scenes observed with random microphone arrangements by decomposing the scene into its constituent sources and their relative presence in each microphone.
Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information
We present a monophonic source separation system that is trained by only observing mixtures with no ground truth separation information.
End-to-end Networks for Supervised Single-channel Speech Separation
The performance of single channel source separation algorithms has improved greatly in recent times with the development and deployment of neural networks.
Learning the Base Distribution in Implicit Generative Models
Popular generative model learning methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple distributions such as isotropic Gaussian.
Generative Adversarial Source Separation
Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density.
Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization
We propose a novel speech enhancement method that is based on a Bayesian formulation of NMF (BNMF).
A State-Space Approach to Dynamic Nonnegative Matrix Factorization
Nonnegative matrix factorization (NMF) has been actively investigated and used in a wide range of problems in the past decade.
End-to-end Source Separation with Adaptive Front-Ends
We present an auto-encoder neural network that can act as an equivalent to short-time front-end transforms.
Sound
Diagonal RNNs in Symbolic Music Modeling
In this paper, we propose a new Recurrent Neural Network (RNN) architecture.
NoiseOut: A Simple Way to Prune Neural Networks
In this paper, we propose NoiseOut, a fully automated pruning algorithm based on the correlation between activations of neurons in the hidden layers.
Bitwise Neural Networks
Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for developing and deploying neural networks whose weight parameters, bias terms, input, and intermediate hidden layer output signals, are all binary-valued, and require only basic bit logic for the feedforward pass.
A Dictionary Learning Approach for Factorial Gaussian Models
We argue that due to the specific structure of the activation matrix $R$ in the shared component factorial mixture model, and an incoherence assumption on the shared component, it is possible to extract the columns of the $O$ matrix without the need for alternating between the estimation of $O$ and $R$.
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
In this paper, we explore joint optimization of masking functions and deep recurrent neural networks for monaural source separation tasks, including monaural speech separation, monaural singing voice separation, and speech denoising.
Spectral Learning of Mixture of Hidden Markov Models
In this paper, we propose a learning approach for the Mixture of Hidden Markov Models (MHMM) based on the Method of Moments (MoM).
Deep learning for monaural speech separation
In this paper, we study deep learning for monaural speech separation.
A Sparse Non-Parametric Approach for Single Channel Separation of Known Sounds
In this paper we present an algorithm for separating mixed sounds from a monophonic recording.
Sparse Overcomplete Latent Variable Decomposition of Counts Data
An important problem in many fields is the analysis of counts data to extract meaningful latent components.
