Picture for Paris Smaragdis

Paris Smaragdis

Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations

Add code
Apr 05, 2024
Viaarxiv icon

Scaling Up Adaptive Filter Optimizers

Add code
Mar 01, 2024
Figure 1 for Scaling Up Adaptive Filter Optimizers
Figure 2 for Scaling Up Adaptive Filter Optimizers
Figure 3 for Scaling Up Adaptive Filter Optimizers
Viaarxiv icon

Sound Source Separation Using Latent Variational Block-Wise Disentanglement

Add code
Feb 08, 2024
Viaarxiv icon

Meta-AF Echo Cancellation for Improved Keyword Spotting

Add code
Dec 17, 2023
Figure 1 for Meta-AF Echo Cancellation for Improved Keyword Spotting
Figure 2 for Meta-AF Echo Cancellation for Improved Keyword Spotting
Figure 3 for Meta-AF Echo Cancellation for Improved Keyword Spotting
Figure 4 for Meta-AF Echo Cancellation for Improved Keyword Spotting
Viaarxiv icon

Audio Editing with Non-Rigid Text Prompts

Add code
Oct 19, 2023
Figure 1 for Audio Editing with Non-Rigid Text Prompts
Figure 2 for Audio Editing with Non-Rigid Text Prompts
Figure 3 for Audio Editing with Non-Rigid Text Prompts
Figure 4 for Audio Editing with Non-Rigid Text Prompts
Viaarxiv icon

Mechatronic Generation of Datasets for Acoustics Research

Add code
Oct 01, 2023
Figure 1 for Mechatronic Generation of Datasets for Acoustics Research
Figure 2 for Mechatronic Generation of Datasets for Acoustics Research
Figure 3 for Mechatronic Generation of Datasets for Acoustics Research
Figure 4 for Mechatronic Generation of Datasets for Acoustics Research
Viaarxiv icon

Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity

Add code
Sep 25, 2023
Figure 1 for Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Figure 2 for Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Figure 3 for Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Figure 4 for Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Viaarxiv icon

Complete and separate: Conditional separation with missing target source attribute completion

Add code
Jul 27, 2023
Figure 1 for Complete and separate: Conditional separation with missing target source attribute completion
Figure 2 for Complete and separate: Conditional separation with missing target source attribute completion
Figure 3 for Complete and separate: Conditional separation with missing target source attribute completion
Figure 4 for Complete and separate: Conditional separation with missing target source attribute completion
Viaarxiv icon

Unsupervised Improvement of Audio-Text Cross-Modal Representations

Add code
May 05, 2023
Figure 1 for Unsupervised Improvement of Audio-Text Cross-Modal Representations
Figure 2 for Unsupervised Improvement of Audio-Text Cross-Modal Representations
Figure 3 for Unsupervised Improvement of Audio-Text Cross-Modal Representations
Figure 4 for Unsupervised Improvement of Audio-Text Cross-Modal Representations
Viaarxiv icon

A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement

Add code
Feb 23, 2023
Figure 1 for A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
Figure 2 for A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
Figure 3 for A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
Figure 4 for A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
Viaarxiv icon