1 code implementation • 11 Oct 2023 • Josh Gardner, Simon Durand, Daniel Stoller, Rachel M. Bittner
Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio.
1 code implementation • 13 Jun 2023 • Simon Durand, Daniel Stoller, Sebastian Ewert
This way, we obtain a novel system that is simple to train end-to-end, can make use of weakly annotated training data, jointly learns a powerful text model, and is tailored to alignment.
1 code implementation • 14 Nov 2019 • Daniel Stoller, Mi Tian, Sebastian Ewert, Simon Dixon
In comparison to TCN and Wavenet, our network consistently saves memory and computation time, with speed-ups for training and inference of over 4x in the audio generation experiment in particular, while achieving a comparable performance in all tasks.
Ranked #2 on Music Modeling on Nottingham
1 code implementation • ICLR 2020 • Daniel Stoller, Sebastian Ewert, Simon Dixon
We apply our method to image generation, image segmentation and audio source separation, and obtain improved performance over a standard GAN when additional incomplete training examples are available.
no code implementations • 21 Apr 2019 • Saumitra Mishra, Daniel Stoller, Emmanouil Benetos, Bob L. Sturm, Simon Dixon
However, this requires a careful selection of hyper-parameters to generate interpretable examples for each neuron of interest, and current methods rely on a manual, qualitative evaluation of each setting, which is prohibitively slow.
1 code implementation • 9 Apr 2019 • Bhusan Chettri, Daniel Stoller, Veronica Morfi, Marco A. Martínez Ramírez, Emmanouil Benetos, Bob L. Sturm
Our ensemble model outperforms all our single models and the baselines from the challenge for both attack types.
Audio and Speech Processing Sound
2 code implementations • 18 Feb 2019 • Daniel Stoller, Simon Durand, Sebastian Ewert
Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications.
9 code implementations • 8 Jun 2018 • Daniel Stoller, Sebastian Ewert, Simon Dixon
Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end.
Ranked #27 on Music Source Separation on MUSDB18
no code implementations • 5 Apr 2018 • Daniel Stoller, Sebastian Ewert, Simon Dixon
A main challenge in applying deep learning to music processing is the availability of training data.
3 code implementations • 31 Oct 2017 • Daniel Stoller, Sebastian Ewert, Simon Dixon
Based on this idea, we drive the separator towards outputs deemed as realistic by discriminator networks that are trained to tell apart real from separator samples.