Academic:

  • Improving cochlear implant users music perception.
    Music appreciation remains rather poor for many Cochlear Implant (CI) users due to their poor pitch perception. Simple music structures with a clear rhythm/beat are well perceived for CI users. By re-mixing the music we are able to simplify the signal to make it more suitable for implantees. But the multitrack recordings necessary to generate a re-mix are not always accessible. To overcome this limitation, we propose to use current source separation state-of-the-art techniques to estimate the multitrack recordings. The perceptual studies are conducted using the Non-negative Matrix Factorization algorithm. Deep Recurrent Neural Networks are also studied for that purpose.
  • Drums Transcription.
    We studied new contributions for audio event detection methods using Non-negative Matrix Deconvolution and the Itakura Saito divergence that improve efficiency and numerical stability, and simplify the generation of target pattern sets. A new approach for handling background sounds is proposed and moreover, a new detection criteria based on estimating the perceptual presence of the target class sources is introduced. Experimental results obtained for drum detection in polyphonic music and drum solos demonstrate the beneficial effects of the proposed extensions. Associated publication.

Non academic:

  • Chord Profiles.
    Pretends to provide a SIMPLE framework where ALL the binary chord profiles are properly defined. Open available on GitHub.
  • How big is the smallest pitch difference between 2 consecutive tones that a human listener can detect?
    The previous research question is answered by means of a perceptual test. It is concluded that the smallest pitch difference between 2 consecutive tones that a musician listener can detect (3.18 MELs) is smaller than the smallest pitch difference perceived by non-musicians (11.41 MELs). Further conclusions are published here.