Research programs

Learnable signal representations

Wavelets, wavelet packets and fractional superlets as adaptive representations for emotion analysis and speech enhancement.

Research direction

A signal representation determines which details a model can retain. This work brings multiresolution signal processing into trainable neural networks, with filters and denoising operations learned alongside the task.

Related studies include SigWavNet, learnable wavelet-packet models, a bidirectional autoencoder for speech enhancement, and fractional superlets with a spectro-temporal emotion encoder. Papers and code are linked as distinct research outputs.

  • Which time-frequency resolutions are useful for a task?
  • How can learned denoising preserve meaningful speech structure?

Sign in to save this record →