Voice Doesn't Exist – Generative Voice AI

Re:Voice Doesn't Exist – Generative Voice AI by angusturner on Friday January 13, 2023 @09:00AM (#34367801)

As someone working on singing synthesis, I know how hard it is to get that last 10% quality that makes a human listener instantly recognise if the voice is real or generated.

These are really impressive results! For anyone interested, my team’s singing work: https://youtu.be/LPy20zSWhZA)

[ Parent | on HN ]

Re:Voice Doesn't Exist – Generative Voice AI by meremortals on Friday January 13, 2023 @10:16AM (#34368858)

Very well done! Any suggestions on where/how one might learn to do something similar? I love the idea of being able to swap singers on a given track

[ Parent | on HN ]

Re:Voice Doesn't Exist – Generative Voice AI by imtringued on Friday January 13, 2023 @05:38PM (#34374882)

If you are going to have such an intensive particle effect in your videos at least bother to upload a 4k version so there is a tiny chance that not every single frame consists of nothing but artifacts.

Also don't put gumi and English in the same search query on YouTube. I don't know how they did it but the voices from six years ago sound better than SOTA TTS based on deep learning today...

[ Parent | on HN ]

Re:Voice Doesn't Exist – Generative Voice AI by singedproxy on Friday January 13, 2023 @07:50PM (#34376042)

Clearly the point of the video is its AUDIO content, not the visuals. The lack of a "4k version" does not make any difference other than saving you bandwith :-)

[ Parent | on HN ]