Style transfer of audio effects with differentiable signal processing

CJ Steinmetz, NJ Bryan, JD Reiss - arXiv preprint arXiv:2207.08759, 2022 - arxiv.org
We present a framework that can impose the audio effects and production style from one
recording to another by example with the goal of simplifying the audio production process …

Differentiable signal processing with black-box audio effects

MAM Ramírez, O Wang, P Smaragdis… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
We present a data-driven approach to automate audio signal processing by incorporating
stateful third-party, audio effects as layers within a deep neural network. We then train a …

Early prediction of breast cancer recurrence for patients treated with neoadjuvant chemotherapy: a transfer learning approach on DCE-MRIs

MC Comes, D La Forgia, V Didonna, A Fanizzi, F Giotta… - Cancers, 2021 - mdpi.com
Simple Summary An early prediction of Breast Cancer Recurrence (BCR) for patients
undergoing neoadjuvant chemotherapy (NACT) could better guide clinicians in the …

Learning representations by humans, for humans

S Hilgard, N Rosenfeld, MR Banaji… - … on machine learning, 2021 - proceedings.mlr.press
When machine predictors can achieve higher performance than the human decision-makers
they support, improving the performance of human decision-makers is often conflated with …

Inversynth: Deep estimation of synthesizer parameter configurations from audio signals

O Barkan, D Tsiris, O Katz… - IEEE/ACM Transactions …, 2019 - ieeexplore.ieee.org
Sound synthesis is a complex field that requires domain expertise. Manual tuning of
synthesizer parameters to match a specific sound can be an exhaustive task, even for …

Unknown-box approximation to improve optical character recognition performance

A Randika, N Ray, X Xiao, A Latimer - … 5–10, 2021, Proceedings, Part I 16, 2021 - Springer
Optical character recognition (OCR) is a widely used pattern recognition application in
numerous domains. There are several feature-rich, general-purpose OCR solutions …

An investigation into neural arithmetic logic modules

B Mistry - 2023 - eprints.soton.ac.uk
The human ability to learn and reuse skills in a systematic manner is critical to our daily
routines. For example, having the skills for executing the basic arithmetic operations …

A primer for neural arithmetic logic modules

B Mistry, K Farrahi, J Hare - Journal of Machine Learning Research, 2022 - jmlr.org
Neural Arithmetic Logic Modules have become a growing area of interest, though remain a
niche field. These modules are neural networks which aim to achieve systematic …

Document Image Cleaning using Budget-Aware Black-Box Approximation

G Tata, K Singh, E Van Oeveren, N Ray - arXiv preprint arXiv:2306.13236, 2023 - arxiv.org
Recent work has shown that by approximating the behaviour of a non-differentiable black-
box function using a neural network, the black-box can be integrated into a differentiable …

Stealing black-box functionality using the deep neural tree architecture

D Teitelman, I Naeh, S Mannor - arXiv preprint arXiv:2002.09864, 2020 - arxiv.org
This paper makes a substantial step towards cloning the functionality of black-box models by
introducing a Machine learning (ML) architecture named Deep Neural Trees (DNTs). This …