Popular music is often composed of an accompaniment and a lead component, the latter
typically consisting of vocals. Filtering such mixtures to extract one or both components has …

Deep neural networks (DNN) techniques have become pervasive in domains such as
natural language processing and computer vision. They have achieved great success in …

The performance of music source separation (MSS) models has been greatly improved in
recent years thanks to the development of novel neural network architectures and training …

We introduce PixelPlayer, a system that, by leveraging large amounts of unlabeled videos,
learns to locate image regions which produce sounds and separate the input sounds into a …

Music source separation is the task of decomposing music into its constitutive components,
eg, yielding separated stems for the vocals, bass, and drums. Such a separation has many …

The decomposition of a music audio signal into its vocal and backing track components is
analogous to image-to-image translation, where a mixed spectrogram is transformed into its …

Most speech processing techniques use magnitude spectrograms as front-end and are
therefore by default discarding part of the signal: the phase. In order to overcome this …

Recent deep learning approaches have achieved impressive performance on visual sound
separation tasks. However, these approaches are mostly built on appearance and optical …

Sounds originate from object motions and vibrations of surrounding air. Inspired by the fact
that humans is capable of interpreting sound sources from how objects move visually, we …

Recent deep learning approaches have achieved impressive performance on speech
enhancement and separation tasks. However, these approaches have not been investigated …