top of page
main_v6_edited.jpg

December 2023

We explore the task of hierarchical distance-based speech separation defined on a hyperbolic manifold. Paper will be posted soon !

conference

speech separation

jp_overall.png

July 2023

We extend the cocktail fork source separation formulation by tackling transcription for each of the three sources involved: audio tagging for music and sound effect, and ASR for speech

journal paper

source separation

audio tagging

hyperbolic.png

December 2022

We introduce a framework for audio source separation using embeddings on a hyperbolic manifold.

conference

source separation

interactive system

mb_harpnet.png

December 2022

A multi-band approach to neural audio coding, which exploits the U-Net upsampling capabilities and offers band-specific bitrate assignments. 

conference

neural audio coding

SpaIn-Net-Overview.png

May 2022

We present an interactive music source separation system allowing a user to specify the spatial location of the instruments of interest. We explore various conditioning mechanisms ranging from simple concatenation to positional encoding and AdaIN.

conference

source separation

interactive system

dnr_fork.jpg

May 2022

We introduce a new source separation dataset, Divide and Remaster (DnR), for training and testing algorithms aiming at separating monaural audio signals into speech, music, and sound effects/background stems.

conference

dataset

source separation

merl

E66klsZWUAY3QBI.jpeg

October 2021

Our paper entitled "HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding" has been accepted to the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics !

conference

neural audio coding

autoencoder

ismir_logo.png

August 2020

Thrilled to announce that our paper entitled "Deep Learning Based Source Separation Applied to Choir Ensembles" has been accepted to the 21st International Society for Music Information Retrieval Conference !

conference

music information retrieval

source separation

c-unet-f0.png

January 2020

In this second part, we explore network conditioning for source separation tasks, using the sources' fundamental frequency as control input.

conditioned u-net

source separation

film layer

satb_separation_icon_website-5.png

January 2020

Musical source separation for SATB choral recordings, performed in both the waveform and spectral domain.

python

source separation

tensorflow

source_number_icon_website-2.png

March 2020

Source count for audio signals via multi-fundamental frequency contour analysis.

python

f0 estimation

tensorflow

Screen Shot 2020-04-13 at 10.03.01 PM.pn

February 2020

System designed in PureData, which assimilates and learns from musical performances using Markov models.

pure data

performance

markov model

csconvolve_thumb.png

May 2016

An iPad app exploring different spectral synthesis and processing techniques, such as convolution, morphing and cross synthesis from a practical perspective.

csound

iPad app

objective-c

spectral processing

splash_jam.png

January 2016

Fun and creative music making app; with csJam, you can improvise, perform, sequence, and compose with a variety of synthetic and sampled instruments.

csound

iPad app

objective-c

step-sequencer

igenerate_thumbnail.png

March 2015

iPad app exploiting musical concepts such as question-answer, motifs, and transposition to generate music algorithmically in interaction with its user.

csound

iPad app

objective-c

generative music

Screen Shot 2020-04-13 at 7.45.41 PM.png

March 2015

Various physical model systems using noise as their sole signal source in order to generate various sound effects.

max/msp

noise-based

physical model

Screen Shot 2020-04-11 at 12.38.51 PM.pn

September 2015

A simple yet powerful program written in C  for algorithmic music generation.

c programming

csound

generative music

bottom of page