The deep learning based time-domain models, eg Conv-TasNet, have shown great potential
in both single-channel and multi-channel speech enhancement. However, many …

We investigate which loss functions provide better separations via benchmarking an
extensive set of those for music source separation. To that end, we first survey the most …

We introduce PodcastMix, a dataset formalizing the task of separating background music
and foreground speech in podcasts. We aim at defining a benchmark suitable for training …

Universal sound separation consists of separating mixes with arbitrary sounds of different
types, and permutation invariant training (PIT) is used to train source agnostic models that …

Existing speech separation models based on deep learning typically generalize poorly due
to domain mismatch. In this paper, we propose SpeakerAugment (SA), a data augmentation …

Speech separation dataset typically consists of hard and non-hard samples, and the former
is minority and latter majority. The data imbalance problem biases the model towards non …

This study emphasizes the significance of exploring distance-based source separation
(DSS) in outdoor environments. Unlike existing studies that primarily focus on indoor …

Speech separation separates the speech of interest from background noise (speech
enhancement) or interfering speech (speaker separation). While the human auditory system …

Speaker separation aims to extract multiple voices from a mixed signal. In this paper, we
propose two speaker-aware designs to improve the existing speaker separation solutions …

This thesis proposes a journey into sound processing through deep learning, particularly
generative models, exploring the compositional structure of sound, which is layered in …