Taras Sereda

IMG_4285.jpg

taras.y.sereda@proton.me

I’m a Machine Learning Engineer and DIY Enthusiast. I’m providing consultancy services concerning speech and audio processing. My interests lie in self-supervised methods and discrete representations. I’m excited about potential of deep learning for material science.

selected publications

  1. paper
    Pheme: Efficient and Conversational Speech Generation
    Budzianowski, Paweł, Sereda, Taras, Cichy, Tomasz, and Vulić, Ivan
    2024
  2. paper
    Transcribe, Align and Segment: Creating speech datasets for low-resource languages
    Sereda, Taras
    2024