Generative audio refers to the creation of audio files from databases of audio clips.^{[citation needed]} This technology differs from synthesized voices such as Apple's Siri or Amazon's Alexa, which use a collection of fragments that are stitched together on demand.

Generative audio works by using neural networks to learn the statistical properties of an audio source, then reproduces those properties.^[1]

Implications

With this technology, a person's voice can be replicated to speak phrases that they may have never spoken. This could lead to a synthetic version of a public figure's voice being used against them.^[2]

Technology

This method uses a generative adversarial network (GAN), a deep machine learning technique where two machine learning models work against each other to create realistic audio.^[3]

See also

• Generative art
• Generative music

References