Generating a stereophonic presentation from a monophonic audio signal is...
Recent work has studied text-to-audio synthesis using large amounts of p...
The field of steganography has experienced a surge of interest due to th...
Recent works have shown the capability of deep generative models to tack...
Universal sound separation consists of separating mixes with arbitrary s...
We introduce PodcastMix, a dataset formalizing the task of separating
ba...
Removing background noise from speech audio has been the subject of
cons...
We investigate which loss functions provide better separations via
bench...
Upsampling artifacts are caused by problematic upsampling layers and due...
Communication technologies like voice over IP operate under constrained
...
Steganography comprises the mechanics of hiding data in a host media tha...
Score-based generative models provide state-of-the-art quality for image...
The current paradigm for creating and deploying immersive audio content ...
We study permutation invariant training (PIT), which targets at the
perm...
A number of recent advances in audio synthesis rely on neural upsamplers...
Applications of deep learning to automatic multitrack mixing are largely...
Most existing datasets for sound event recognition (SER) are relatively ...
Automatic speech quality assessment is an important, transversal task wh...
Essentia is a reference open-source C++/Python library for audio and mus...
Conv-TasNet is a recently proposed waveform-based deep neural network th...
Pronounced as "musician", the musicnn library contains a set of pre-trai...
Most of the currently successful source separation techniques use the
ma...
We investigate supervised learning strategies that improve the training ...
This paper describes Task 2 of the DCASE 2018 Challenge, titled
"General...
The computer vision literature shows that randomly weighted neural netwo...
The lack of data tends to limit the outcomes of deep learning research -...
We approach the singing phrase audio to score matching problem by using
...
This paper introduces a new score-informed method for the segmentation o...