Page history

Juho Kunsola

linking to the Stop-Synthetic-Filth.org for most recent information

Juho Kunsola

work on the formulation of the definition

Juho Kunsola

→‎Timeline of digital sound-alikes: + In 2018 Conference on Neural Information Processing Systems the work 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis'

Juho Kunsola

starting on == Timeline of digital sound-alikes ==

Juho Kunsola

+ A picture of a w:spectrogram of a male voice saying 'nineteenth century'

Juho Kunsola

move the actually realized crimes up

Juho Kunsola

Changed a heading to == Example of a hypothetical digital sound-alike attack ==

Juho Kunsola

just the URL in ref

Juho Kunsola

+ As of 2019 Symantec research knows of 3 cases where digital sound-alike technology has been used for crimes + <ref name="WaPo2019">

Juho Kunsola

+ == Documented digital sound-alike attacks == + 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft', a 2019 Washington Post article

Juho Kunsola

+ transcluded {{wikipedia::speech synthesis}}

Juho Kunsola

+ Merlin

Juho Kunsola

+== Examples of speech synthesis software not quite able to fool a human yet == + Lyrebird.ai + CandyVoice.com

Juho Kunsola

+ == See also in Wikipedia == + w:Speech synthesis

Juho Kunsola

→‎Examples of software capable to make a digital sound-alike: + link to a youtube showing the Adobe MAX 2016, where w:Adobe Voco was first demonstrated to a select audience

Juho Kunsola

+ == See also in Ban Covert Modeling! wiki ==

Juho Kunsola

+ examples of voice thieving software: w:Adobe Inc.'s Voco unreleased prototype publicly demonstrated in 2016 + w:DeepMind's w:WaveNet that was acquired by w:Google in 2014

Juho Kunsola

On digital sound-alikes