b'Joan Serr\xc3\xa0'

research

∙ 06/26/2023

Mono-to-stereo through parametric stereo generation

Generating a stereophonic presentation from a monophonic audio signal is...

0 Joan Serrà, et al. ∙

research

∙ 06/16/2023

CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models

Recent work has studied text-to-audio synthesis using large amounts of p...

0 Hao-Wen Dong, et al. ∙

research

∙ 10/26/2022

Full-band General Audio Synthesis with Score-based Diffusion

Recent works have shown the capability of deep generative models to tack...

0 Santiago Pascual, et al. ∙

research

∙ 10/23/2022

Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation

Single channel target speaker separation (TSS) aims at extracting a spea...

0 Xiaoyu Liu, et al. ∙

research

∙ 10/21/2022

Adversarial Permutation Invariant Training for Universal Sound Separation

Universal sound separation consists of separating mixes with arbitrary s...

0 Emilian Postolache, et al. ∙

research

∙ 06/07/2022

Universal Speech Enhancement with Score-based Diffusion

Removing background noise from speech audio has been the subject of cons...

0 Joan Serrà, et al. ∙

research

∙ 02/16/2022

On loss functions and evaluation metrics for music source separation

We investigate which loss functions provide better separations via bench...

14 Enric Gusó, et al. ∙

research

∙ 11/23/2021

Upsampling layers for music source separation

Upsampling artifacts are caused by problematic upsampling layers and due...

0 Jordi Pons, et al. ∙

research

∙ 09/30/2021

Assessing Algorithmic Biases for Musical Version Identification

Version identification (VI) systems now offer accurate and scalable solu...

0 Furkan Yesiler, et al. ∙

research

∙ 09/06/2021

Audio-based Musical Version Identification: Elements and Challenges

In this article, we aim to provide a review of the key ideas and approac...

0 Furkan Yesiler, et al. ∙

research

∙ 07/07/2021

Adversarial Auto-Encoding for Packet Loss Concealment

Communication technologies like voice over IP operate under constrained ...

0 Santiago Pascual, et al. ∙

research

∙ 04/09/2021

Heaps' Law and Vocabulary Richness in the History of Classical Music Harmony

Music is a fundamental human construct, and harmony provides the buildin...

0 Marc Serra-Peralta, et al. ∙

research

∙ 04/08/2021

On tuning consistent annealed sampling for denoising score matching

Score-based generative models provide state-of-the-art quality for image...

0 Joan Serrà, et al. ∙

research

∙ 01/06/2021

Investigating the efficacy of music version retrieval systems for setlist identification

The setlist identification (SLI) task addresses a music recognition use ...

0 Furkan Yesiler, et al. ∙

research

∙ 10/27/2020

Upsampling artifacts in neural audio synthesis

A number of recent advances in audio synthesis rely on neural upsamplers...

0 Jordi Pons, et al. ∙

research

∙ 10/20/2020

Automatic multitrack mixing with a differentiable mixing console of neural audio effects

Applications of deep learning to automatic multitrack mixing are largely...

0 Christian J. Steinmetz, et al. ∙

research

∙ 10/07/2020

Less is more: Faster and better music version identification with embedding distillation

Version identification systems aim to detect different renditions of the...

0 Furkan Yesiler, et al. ∙

research

∙ 10/01/2020

SESQA: semi-supervised learning for speech quality assessment

Automatic speech quality assessment is an important, transversal task wh...

0 Joan Serrà, et al. ∙

research

∙ 10/28/2019

Accurate and Scalable Version Identification Using Musically-Motivated Embeddings

The version identification (VI) task deals with the automatic detection ...

0 Furkan Yesiler, et al. ∙

research

∙ 09/25/2019

Input complexity and out-of-distribution detection with likelihood-based generative models

Likelihood-based generative models are a promising resource to detect ou...

0 Joan Serrà, et al. ∙

research

∙ 06/03/2019

Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion

End-to-end models for raw audio generation are a challenge, specially if...

0 Joan Serrà, et al. ∙

research

∙ 04/06/2019

Towards Generalized Speech Enhancement with Generative Adversarial Networks

The speech enhancement task usually consists of removing additive noise ...

0 Santiago Pascual, et al. ∙

research

∙ 04/06/2019

Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks

Learning good representations without supervision is still an open issue...

0 Santiago Pascual, et al. ∙

research

∙ 10/24/2018

Training neural audio classifiers with few data

We investigate supervised learning strategies that improve the training ...

0 Jordi Pons, et al. ∙

research

∙ 08/31/2018

Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks

Most methods of voice restoration for patients suffering from aphonia ei...

0 Santiago Pascual, et al. ∙

research

∙ 08/31/2018

Self-Attention Linguistic-Acoustic Decoder

The conversion from text to speech relies on the accurate mapping from l...

0 Santiago Pascual, et al. ∙

research

∙ 06/07/2018

Assessing the impact of machine intelligence on human behaviour: an interdisciplinary endeavour

This document contains the outcome of the first Human behaviour and mach...

0 Emilia Gómez, et al. ∙

research

∙ 06/07/2018

There goes Wally: Anonymously sharing your location gives you away

With current technology, a number of entities have access to user mobili...

0 Apostolos Pyrgelis, et al. ∙

research

∙ 05/10/2018

Towards a universal neural network encoder for time series

We study the use of a time series encoder to learn representations that ...

0 Joan Serrà, et al. ∙

research

∙ 01/04/2018

Overcoming catastrophic forgetting with hard attention to the task

Catastrophic forgetting occurs when a neural network loses the informati...

0 Joan Serrà, et al. ∙

research

∙ 12/19/2017

Continual Prediction of Notification Attendance with Classical and Deep Network Approaches

We investigate to what extent mobile use patterns can predict -- at the ...

0 Kleomenis Katevas, et al. ∙

research

∙ 12/18/2017

Language and Noise Transfer in Speech Enhancement Generative Adversarial Network

Speech enhancement deep learning systems usually require large amounts o...

0 Santiago Pascual, et al. ∙

research

∙ 09/29/2017

MobInsight: A Framework Using Semantic Neighborhood Features for Localized Interpretations of Urban Mobility

Collective urban mobility embodies the residents' local insights on the ...

0 Souneil Park, et al. ∙

research

∙ 06/13/2017

Getting deep recommenders fit: Bloom embeddings for sparse binary input/output networks

Recommendation algorithms that incorporate techniques from deep learning...

0 Joan Serrà, et al. ∙

research

∙ 03/28/2017

SEGAN: Speech Enhancement Generative Adversarial Network

Current speech enhancement techniques operate on the spectral domain and...

0 Santiago Pascual, et al. ∙

research

∙ 11/16/2015

A genetic algorithm to discover flexible motifs with support

Finding repeated patterns or motifs in a time series is an important uns...

0 Joan Serrà, et al. ∙

research

∙ 01/29/2015

Particle swarm optimization for time series motif discovery

Efficiently finding similar segments or motifs in time series data is a ...

0 Joan Serrà, et al. ∙

research

∙ 01/16/2014

An Empirical Evaluation of Similarity Measures for Time Series Classification

Time series are ubiquitous, and a measure to assess their similarity is ...

0 Joan Serrà, et al. ∙

research

∙ 08/29/2011

Characterization and exploitation of community structure in cover song networks

The use of community detection algorithms is explored within the framewo...

0 Joan Serrà, et al. ∙

Joan Serrà

Featured Co-authors