Hacker News new | past | comments | ask | show | jobs | submit login

Nor would anonymising a voice recording (presumably by doing some sort of frequency-___domain transform) be of much use to them for the sort of thing they're using them for - training speech recognition on a wide variety of different voices.



It's virtually impossible to anonymize voice. Except by doing voice to text, and then synthesize voice.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: