Now we can have audiobooks read by anyone we like!
They can direct us to our destination!
They can speak at our funeral, being long dead themselves (as long as there is sufficient training material recorded).
The future is awesome.
AI Clones Your Voice After Listening for 5 Seconds (2018)
101–110 of 338 posts
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#102I wonder what the legal implications of this alongside similar developments like deepfakes are going to be in the next couple years. We're already having fraudsters impersonate CEOs using Deep learning-aided Voice generation[1] due to just how low the barrier of entry is now. There's already a public implementation of the paper out [2]! [1]: https://www.wsj.com/articles/fraudsters-use-ai-to-mimic-ceos... [2]: https:/…
Currently watching UK: https://mobile.twitter.com/FutureAdvocacy/status/11942824810...
Sorry for the Twitter link but Future Advocacys website seems to be down.
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#103The malign applications of this technology greatly outweigh the benign. Discuss.
I think there are many benign applications, and definitely a massive potential for abuse. In practice, it will be used mostly for benign applications, I think, but due to the outsized impact, you could still say the malign applications outweigh. However, what I found reassuring is that the paper actually addresses these concerns: "However, it is also important to note the potential for misuse of this technology, for…
I'm guessing this will just be used as an excuse by Google to prevent this technology from being easily or fully accessible to others.
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#104And no one will be able to independently reproduce these results. As with most Google speech research publications.
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#105So....I'm going to paste the abstract here because the headline is incredibly misleading and should be changed. >Abstract: We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained…
Do you want to elaborate on how the title is misleading? From reading the abstract it seems accurate to me.
"AI Clones Your Voice" implies there might be something on the linked page that involves an AI cloning my voice. Maybe a way to record a few phrases, maybe a text to speech that then uses my voice. Something like that.
This does not do that - only provides pre-rendered samples, kinda disappointing. Impressive, but disappointing.
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#106Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#107It will be interesting to see if these made-up AI voices can deliver jokes with the same tonality and delivery as good comedians can. I'm just a layman but it feels like a hard problem to solve.
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#108AI can make decisions, create deep fakes, and now, clone voices. It may be that the next big business opportunity lies in creating 'anti-AI' technology just as it did with antiviruses in the 90's and 2000's
Wouldn't an AI-detector just end up being used like a benchmark for fine-tuning AIs though?
Yep! Adversarial learning. Whoever has the best math and compute wins.
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#109How long until we have the napster equivalent of voices? Voicester?
Re: AI Clones Your Voice After Listening for 5 Seconds (2018)
#110Maybe after all these years of people disconnecting physically, using more phones and apps to communicate or meet we will go back to the fundamental real world human connection because that's the only one that can be trusted to be genuine.
And the digital world will be left out because not trustworthy. Is this where we are heading to?