things that keep me busy

.js-id-Topics

ACMus

Computational musicology, machine learning and Colombian music.

Music Education

Technologies and MIR for music education.

Music Information Retrieval

MIR research, interests and projects

Sound Source Separation

Sound source separation applied to music and audio.

The Scottish fiddle

Analysis of micro-timing variations in Shetland fiddle music.

Recent publications

Transfer learning from speech to music: towards language-sensitive emotion recognition models

In this study, we address emotion recognition using unsupervised feature learning from speech data, and test its transferability to …

Analyzing the potential of pre-trained embeddings for audio classification tasks

In the context of deep learning, the availability of large amounts of training data can play a critical role in a model’s …

Examining the Mapping Functions of Denoising Autoencoders in Singing Voice Separation

The goal of this article is to investigate what singing voice separation approaches based on neural networks learn from the data. We …

Musical Source Separation: An Introduction

Many people listen to recorded music as part of their everyday lives, e.g., from radio or TV programs, compact discs, downloads, or, …

Microtiming analyisis in traditional Shetland Fiddle Music

This work aims to characterize microtiming variations in traditional Shetland fiddle music. These microtiming variations dictate the …

Music and Audio R&D

Biography

I am a senior scientist at AudioSourceRe in Ireland, where I develop music source separation technologies. My PhD work started off from my interest to apply MIR technologies in music education. Since then, I have worked in sound source separation, music information retrieval, computational musicology, audio processing, among other research topics. Since 2012, I am the CSO and co-founder of Songquito, a small company that builds music education apps such as [Song2See] (https://www.song2see.com). I previously worked at A*STAR in Singapore, and at Fraunhofer IDMT in Germany. I have worked in a number of applied research projects with industry partners, as well as in European, German, and Asian research projects.

Interests

  • Music and Audio Information Retrieval
  • Sound Source Separation
  • Computational Musicology

Education

  • PhD in Media Technology, 2014

    Fraunhofer IDMT - TU Ilmenau

  • MSc in Music Engineering, 2009

    University of Miami

  • BA in Music Saxophone, 2007

    Universidad de Antioquia

  • BSc in Electronic Engineering, 2005

    Universidad Pontificia Bolivariana