Now showing items 1-3 of 3

    • A Comparative Analysis Of Latent Regressor Losses For Singing Voice Conversion 

      O'Connor, B; Dixon, S; Sound and Music Computing (SMC Network, 2023-06-12)
      Previous research has shown that established techniques for spoken voice conversion (VC) do not perform as well when applied to singing voice conversion (SVC). We propose an alternative loss component in a loss function ...
    • An Exploratory Study on Perceptual Spaces of the Singing Voice 

      O'Connor, B; Dixon, S; Fazekas, G; The 2020 Joint Conference on AI Music Creativity (Joint Conference on AI Creativity, 2020-10-19)
      Sixty participants provided dissimilarity ratings between various singing techniques. Multidimensional scaling, class averaging and clustering techniques were used to analyse timbral spaces and how they change between ...
    • Zero-shot Singing Technique Conversion 

      O'Connor, B; Fazekas, G; Dixon, S; Computer Music Multidisciplinary Research (CMMR 2021 Organizing Committee, Japan, 2021-11-15)
      In this paper we propose modifications to the neural network framework, AutoVC for the task of singing technique conversion. This includes utilising a pretrained singing technique encoder which extracts technique information, ...