References

Audiovisual reference material, citing audio examples and relevant artistic work of other artists.

ElevenLabs Anomaly

2024

Generated in 2024, Using ElevenLabs Zero-Shot Voice Cloning Tool as part of research at VocoLab, University College London, see:


Rosi, V., Soopramanien, E. and McGettigan, C. (2025) “Perception and social evaluation of cloned and recorded voices: Effects of familiarity and self-relevance,” Computers in Human Behavior: Artificial Humans, 4, p. 100143. Available at: https://doi.org/10.1016/j.chbah.2025.100143.


Sinewave Speech

2024

Generated in 2024, Using ElevenLabs Zero-Shot Voice Cloning Tool as part of research at VocoLab, University College London, see:


Rosi, V., Soopramanien, E. and McGettigan, C. (2025) “Perception and social evaluation of cloned and recorded voices: Effects of familiarity and self-relevance,” Computers in Human Behavior: Artificial Humans, 4, p. 100143. Available at: https://doi.org/10.1016/j.chbah.2025.100143.


WaveNet Demo

8 September, 2016

Full Demo with Audio Samples at: https://deepmind.google/discover/blog/wavenet-a-generative-model-for-raw-audio/

expected synthesis

expected synthesis

unconditional voice synthesis

speaker #1

unconditional voice synthesis

speaker #2

anomaly

anomaly

unconditional piano synthesis

Chris Darwin, University of Sussex

Sinewave Speech Demonstration: https://users.sussex.ac.uk/~cjd/SWS/index.html

"WaveNets open up a lot of possibilities for TTS, music generation and audio modelling in general. The fact that directly generating timestep per timestep with deep neural networks works at all for 16kHz audio is really surprising, let alone that it outperforms state-of-the-art TTS systems." - Aaron van den Oord, Sander Dieleman, Primary Engineers behind  the WaveNet paper.




Oord, A. van den, Dieleman, S. et al. (2016) “WaveNet: A Generative Model for Raw Audio.” arXiv. Available at: https://doi.org/10.48550/arXiv.1609.03499.

Cited Artists

ElevenLabs Anomaly

2024

Generated in 2024, Using ElevenLabs Zero-Shot Voice Cloning Tool as part of research at VocoLab, University College London, see:


Rosi, V., Soopramanien, E. and McGettigan, C. (2025) “Perception and social evaluation of cloned and recorded voices: Effects of familiarity and self-relevance,” Computers in Human Behavior: Artificial Humans, 4, p. 100143. Available at: https://doi.org/10.1016/j.chbah.2025.100143.


Onyx Ashanti

Exo-Voice, Busking in Berlin Park

click to play