no code implementations • 12 Mar 2024 • Vjosa Preniqi, Iacopo Ghinassi, Kyriaki Kalimeri, Charalampos Saitis
Experiments in an out-of-domain setting, instead, suggest that further work is needed for existing domain adaptation techniques to generalise between different social media platforms, especially for the multi-label task.
no code implementations • 21 Oct 2023 • Jincheng Zhang, Jingjing Tang, Charalampos Saitis, György Fazekas
The diffusion model is trained to generate intermediate music sequences consisting of codebook indexes, which are then decoded to symbolic music using the VQ-VAE's decoder.
no code implementations • 21 Oct 2023 • Jincheng Zhang, György Fazekas, Charalampos Saitis
Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis.
no code implementations • 19 Apr 2023 • Ben Hayes, Charalampos Saitis, György Fazekas
We discuss the discontinuities that arise when mapping unordered objects to neural network outputs of fixed permutation, referred to as the responsibility problem.
no code implementations • 16 Apr 2023 • Kai Siedenburg, Charalampos Saitis
ChatGPT generated semantic profiles that only partially correlated with human ratings, yet showed robust agreement along well-known psychophysical dimensions of musical sounds such as brightness (bright-dark) and pitch height (deep-high).
1 code implementation • 27 Oct 2022 • Rodrigo Diaz, Ben Hayes, Charalampos Saitis, György Fazekas, Mark Sandler
Physical models of rigid bodies are used for sound synthesis in applications from virtual environments to music production.
1 code implementation • 26 Oct 2022 • Ben Hayes, Charalampos Saitis, György Fazekas
Sinusoidal parameter estimation is a fundamental task in applications from spectral analysis to time-series forecasting.
1 code implementation • 2 Sep 2022 • Vjosa Preniqi, Kyriaki Kalimeri, Charalampos Saitis
This study explores the association between music preferences and moral values by applying text analysis techniques to lyrics.
1 code implementation • 10 Apr 2022 • Alejandro Delgado, Charalampos Saitis, Emmanouil Benetos, Mark Sandler
Imitating musical instruments with the human voice is an efficient way of communicating ideas between music producers, from sketching melody lines to clarifying desired sonorities.
no code implementations • 10 Apr 2022 • Alejandro Delgado, Emir Demirel, Vinod Subramanian, Charalampos Saitis, Mark Sandler
Vocal Percussion Transcription (VPT) is concerned with the automatic detection and classification of vocal percussion sound events, allowing music creators and producers to sketch drum lines on the fly.
1 code implementation • 5 Sep 2021 • Russell Sammut Bonnici, Charalampos Saitis, Martin Benning
This research project investigates the application of deep learning to timbre transfer, where the timbre of a source audio can be converted to the timbre of a target audio with minimal loss in quality.
1 code implementation • 11 Jul 2021 • Ben Hayes, Charalampos Saitis, György Fazekas
We present the Neural Waveshaping Unit (NEWT): a novel, lightweight, fully causal approach to neural audio synthesis which operates directly in the waveform domain, with an accompanying optimisation (FastNEWT) for efficient CPU inference.
1 code implementation • 25 May 2021 • Cyrus Vahidi, Charalampos Saitis, György Fazekas
Modulation filter bank representations that have been actively researched as a basis for timbre perception have the potential to facilitate the extraction of perceptually salient features.