This is pretty basic at the moment and it's terrifying. Yeah, it has an MS Sam feel to it, but as the tech improves and we know it will, you could use a service like this to put words in someone's mouth. Think about how you could trip up a CEO or a Politician by playing some random clip that they never said. When that gets into the Zeitgeist judgments will be made in the court of public opinion devoid of facts or real evidence. You could destroy democracy or people's lives with technology like this
Lyrebird – An API to copy the voice of anyone
91–100 of 311 posts
Re: Lyrebird – An API to copy the voice of anyone
#92it's interesting development but it sounds too robotic, there is zero intonation/punctuation, zero variantions in the voice depending on mood of speaker, etc., in the end extremely robotic and if someone really need to fake someone else voice convincingly it would be still easier to hire professional voice imitator
Re: Lyrebird – An API to copy the voice of anyone
#93Does anyone know of any free/open source alternatives to this? Is it too new to expect a FOSS library?
Re: Lyrebird – An API to copy the voice of anyone
#94Linda Tripp approves
Re: Lyrebird – An API to copy the voice of anyone
#95Earlier quoted context omitted.
Well, the question is, do they just need to throw more computational power / training at this algorithm or is that the peak of their implementation? This is something Google has been working a lot on [1] and Baidu also recently posted about their results too [2]. We're definitely pretty close to passing the human detectable level. [1] https://deepmind.com/blog/wavenet-generative-model-raw-audio... [2] http://research…
Google and Baidu have only demonstrated single speaker TTS. Lyrebird's the first to demonstrate being able to generate arbitrary voices. Since this came out of a research lab, I would guess that the quality would only improve if they are given more compute and data.
The Google one is able to generate arbitrary voices based on the recordings used for training. So much so that they made it generate piano music.
Re: Lyrebird – An API to copy the voice of anyone
#96This trump version [1] is quite believable.
[1] https://soundcloud.com/user-535691776/trump-6
Re: Lyrebird – An API to copy the voice of anyone
#97Earlier quoted context omitted.
And Black mirror's "would you like to speak with your dead husband again?"
Forget dead husbands, with this tech, it will be hard to trust anything a politician said. Basically, once they master adding this to video, ANYTHING could be construed against anyone. Want a video of a politician saying "Hitler was right" to cheering masses? Want a video about a president saying it's time to start Nuclear War One? You can make that.
And any genuine recording can be plausibly denied.
Re: Lyrebird – An API to copy the voice of anyone
#98Earlier quoted context omitted.
And Black mirror's "would you like to speak with your dead husband again?"
Forget dead husbands, with this tech, it will be hard to trust anything a politician said. Basically, once they master adding this to video, ANYTHING could be construed against anyone. Want a video of a politician saying "Hitler was right" to cheering masses? Want a video about a president saying it's time to start Nuclear War One? You can make that.
Re: Lyrebird – An API to copy the voice of anyone
#99“Believe only half of what you see and nothing that you hear.” -- Edgar Allan Poe
Re: Lyrebird – An API to copy the voice of anyone
#100Earlier quoted context omitted.
And Black mirror's "would you like to speak with your dead husband again?"
Forget dead husbands, with this tech, it will be hard to trust anything a politician said. Basically, once they master adding this to video, ANYTHING could be construed against anyone. Want a video of a politician saying "Hitler was right" to cheering masses? Want a video about a president saying it's time to start Nuclear War One? You can make that.
We already couldn't trust anything a politician said! But indeed, this is the moral equivalent of how Photoshop has nearly undermined photographic evidence. That leaves video, and it's starting to succumb. Synthetic video AI politician, well, Robert Heinlein wrote _The Moon is a Harsh Mistress_ in 1966.