5 citations · 5 across the 6 of their papers we have counts for
8 papers
Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization
Bernardo Torres, Manuel Moussallam, Gabriel Meseguer-Brocal
Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introdu…
Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport
Bernardo Torres, Alain Riou, Gaël Richard +1
In this paper, we propose an Optimal Transport objective for learning one-dimensional translation-equivariant systems and demonstrate its applicability to single pitch estimation.…
PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
Alain Riou, Bernardo Torres, Ben Hayes +4
In this paper, we introduce PESTO, a self-supervised learning approach for single-pitch estimation using a Siamese architecture. Our model processes individual frames of a Variable…
The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis
Bernardo Torres, Geoffroy Peeters, Gael Richard
We present the Inverse Drum Machine, a novel approach to Drum Source Separation that leverages an analysis-by-synthesis framework combined with deep learning. Unlike recent supervi…
A fully differentiable model for unsupervised singing voice separation
Gael Richard, Pierre Chouteau, Bernardo Torres
A novel model was recently proposed by Schulze-Forster et al. in [1] for unsupervised music source separation. This model allows to tackle some of the major shortcomings of existin…
Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport
Bernardo Torres, Geoffroy Peeters, Gaël Richard
In neural audio signal processing, pitch conditioning has been used to enhance the performance of synthesizers. However, jointly training pitch estimators and synthesizers is a cha…
Singer Identity Representation Learning using Self-Supervised Techniques
Bernardo Torres, Stefan Lattner, Gaël Richard
Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To br…
DOC3-Deep One Class Classification using Contradictions
Sauptik Dhar, Bernardo Gonzalez Torres
This paper introduces the notion of learning from contradictions (a.k.a Universum learning) for deep one class classification problems. We formalize this notion for the widely adop…