I'm a software/algorithm engineer, independent researcher, and a first-year PhD student in the UKRI Centre for Doctoral Training in Artificial Intelligence and Music (AIM) program at C4DM, Queen Mary University of London.

My interests including:

• DSP
• MIR
• Deep Learning/Machine Learning
• Binaural Audio
• Speech Signal Processing
• Other audio-related stuff

I'm also an active user of the Deep Learning framework PyTorch. Some projects I developed and maintained:

• torch_specinv: a collections of spectrogram inversion algorithms.
• torchnmf: a package that can help building complex NMF models.
• constant-memory-waveglow: training waveglow with constant memory cost.
• kazane: simple sinc interpolation for 1D signal in PyTorch.
• torch-fftconv: FFT-based PyTorch convolution operators.

See my website for more details.