Semantic communication is expected to be one of the cores of next-generation AI-based
communications. One of the possibilities offered by semantic communication is the capability …

We present AERO, a audio super-resolution model that processes speech and music
signals in the spectral domain. AERO is based on an encoder-decoder architecture with …

In this manuscript, we propose a novel method to perform audio inpainting, ie, the
restoration of audio signals presenting multiple missing parts. Audio inpainting can be …

Restoring degraded music signals is essential to enhance audio quality for downstream
music manipulation. Recent diffusion-based music restoration methods have demonstrated …

In recent years, novel communication strategies have emerged to face the challenges that
the increased number of connected devices and the higher quality of transmitted information …

We address the task of blind 'zero-shot'audio signal denoising and inpainting. In the blind
zero-shot setting, only the corrupted audio signal is used for signal restoration (no other …

In audio recognition, improving the accuracy and generalizability of Pretrained Audio Neural
Networks (PANNs) remains challenging. This study introduces Randomized Area Ratio …

Music is a combination of the human voice and instruments that bring beauty to the listener.
Many people like music to create an atmosphere or atmosphere. In the field of computer …

This paper proposes an unsupervised DNN-based speech enhancement approach founded
on deep priors (DPs). Here, DP signifies that DNNs are more inclined to produce clean …

The present dissertation is divided in two parts. In the first one, we address two inverse
problems, namely compressed sensing (CS) and speech denoising, through the lens of the …