About me

I am a postdoctoral researcher at the Technical University of Denmark, where I also completed my PhD on deep learning-based speech enhancement. Previously, I was a Senior DSP Engineer at Demant. My research interests include audio signal processing, speech enhancement, diffusion models, out-of-distribution generalization, and model-based hearing loss compensation.

I grew up in Colombia, Ivory Coast, Turkey, and Peru. I can speak English, French, Spanish, and Danish. I play the bass in a band, collect vinyl records, and occasionally DJ at parties. I enjoy playing video games, especially Dota 2, in which I used to be a highly ranked player. Other hobbies include tennis, electronics, photography, and chess. I love dogs.

Here is a list of conferences I like to keep an eye on.

Preprints

• Absorbing Discrete Diffusion for Speech Enhancement
  P. Gonzalez
  [Audio examples]

Publications

• Controllable Joint Noise Reduction and Hearing Loss Compensation Using a Differentiable Auditory Model
  P. Gonzalez, T. Dau, and T. May
  The 6th Clarity Workshop on Improving Speech-in-Noise for Hearing Devices, 2025
• Investigating the Design Space of Diffusion Models for Speech Enhancement
  P. Gonzalez, Z.-H. Tan, J. Østergaard, J. Jensen, T. S. Alstrøm, and T. May
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024
• The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems
  P. Gonzalez, Z.-H. Tan, J. Østergaard, J. Jensen, T. S. Alstrøm, and T. May
  IEEE Signal Processing Letters, 2024
  [Audio examples]
• Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler
  P. Gonzalez, Z.-H. Tan, J. Østergaard, J. Jensen, T. S. Alstrøm, and T. May
  IEEE International Conference on Acoustics, Speech and Signal Processing, 2024
• Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments
  P. Gonzalez, T. S. Alstrøm, and T. May
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
• On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems
  P. Gonzalez, T. S. Alstrøm, and T. May
  IEEE International Conference on Acoustics, Speech and Signal Processing, 2023