Our team at Singapore University of Technology and Design (SUTD) is looking for an RA for 6 months to help develop nnAudio. You will be joining our team in music/audio/vision AI supervised by Prof. Dorien Herremans. More information on the music/audio team at dorienherremans.com/team. You will be working on the PyTorch audio processing tool nnAudio developed by Cheuk Kin Wai at our lab.

Required skill set:
- expert in audio signal processing (e.g. discrete Fourier transform, audio downsampling)
- savvy programmer with experience in PyTorch and Python
- creative problem solver- good academic writing skills
- BA in computer science, signal processing, or related
- knowledgeable in 1D and 2D convolutional neural networks

The main tasks include porting functions from librosa and Matlab to PyTorch such as (but not exhaustive):
- Inverse constant-Q transform (ICQT)
- Variable-Q Transform
- Invertible Mel spectrogram

Secondary tasks include code refactoring and keeping the documentation page updated, and demo/tutorial writing.

This is a short term contract, but could be a stepping stone for a PhD in audio signal processing and deep learning for audio/speech. For any info, feel free to contact me. Please email your application, including your CV, and the name/email of a reference, to dorien_herremans [ad] sutd.edu.sg with subject [application RA nnAudio].