Centre for Innovation in Computing at Lassonde

Close mobile menu

Vassilios Tzerpos

Associate Professor, EECS Department
Member, IC@L

Website | Email

2021 – 2022 Research Highlights

Deep learning applications for audio and music

My research interests are in deep learning applications for audio and music. Research projects in the APTLY lab that I direct include detection of generated speech, spoken language identification, and deep learning-based sound design. I am also interested in music classification, music transcription, as well as music generation. I have also recently started a research program on open education resources and the automatic derivation of learning paths.

Research Highlights

  1. “Synthetic Speech Detection Using Deep Neural Networks”,
    Ricardo Reimao and Vassilios Tzerpos,
    to be submitted to the 2021 IEEE International Conference on Speech Technology and
    Human-Computer Dialogue (SpeD).
  2. “Evaluating The Effects of Timbre Transfer on Multiple Instruments”, Pedro Casas and Vassilios Tzerpos, in preparation.
  3. “Spoken Language Identification Using Acoustic Features and Deep Neural Networks”, by Rajshree Daulatabad and Vassilios Tzerpos, in preparation.
  4. “Music-STAR: A Style Transforming system for Audio-based Rearrangement”, by Mahshid Alinoori and Vassilios Tzerpos, in preparation.
  5. MITACS Accelerate: “Ultrasound image analysis for identifying blood in an existing effusion in knee joint”, $15,000.