3,958
edits
Synthetic human-like fakes: Difference between revisions
m
minor fmt
Juho Kunsola (talk | contribs) (→2020's synthetic human-like fakes: January 5th Microsoft researchers announced VALL-E - Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (at microsoft.com) that is able to thieve a voice from only 3 seconds of sample and it is also) |
Juho Kunsola (talk | contribs) m (minor fmt) |
||
| Line 45: | Line 45: | ||
When it cannot be determined by human testing or media forensics whether some fake voice is a synthetic fake of some person's voice, or is it an actual recording made of that person's actual real voice, it is a pre-recorded '''[[Synthetic human-like fakes#Digital sound-alikes|digital sound-alike]]'''. | When it cannot be determined by human testing or media forensics whether some fake voice is a synthetic fake of some person's voice, or is it an actual recording made of that person's actual real voice, it is a pre-recorded '''[[Synthetic human-like fakes#Digital sound-alikes|digital sound-alike]]'''. | ||
Real-time digital look-and-sound-alike in a video call was used to defraud a substantial amount of money in 2023.<ref name="Reuters real-time digital look-and-sound-alike crime 2023"> | '''Real-time digital look-and-sound-alike''' in a video call was used to defraud a substantial amount of money in 2023.<ref name="Reuters real-time digital look-and-sound-alike crime 2023"> | ||
{{cite web | {{cite web | ||
| url = https://www.reuters.com/technology/deepfake-scam-china-fans-worries-over-ai-driven-fraud-2023-05-22/ | | url = https://www.reuters.com/technology/deepfake-scam-china-fans-worries-over-ai-driven-fraud-2023-05-22/ | ||