Papers

Overview

Academic publications

Papers

Voice anonymization in urban sound recordings

In this paper, we propose an anomization method that obfsucate the content and msask the speaker identity, while preserving the acoustic scene. s

View details

Source separation & Data augmentation

In this paper, we present our data augmentation algorithm, tailored for singing voice extraction

View Details

Structure estimation

We investigated different input representation to detect music structure boundaries.

View Details

DALI dataset

Ⓒ Gabriel Meseguer Brocal

We constructed the largest dataset of audio and lyrics aligned, using singing voice detection with deep learning.

View details

DALI dataset - Second paper

Second paper on the DALI dataset, presenting 2nd version. An human evaluation of the produced alignment is also presented.

View details