Timeline for Is changing pitch enough for anonymizing a person's voice?
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 10, 2020 at 15:48 | comment | added | MSalters | Weird that this is downvoted so heavily. It's 100% correct. It's easy to artificially synthesize a hundred hours of pitch-shifted audio, and feed that to a ML. It will learn how to un-shift the audio. MFCC's are indeed a very common audio transform used in STT, exactly because the transform removes speaker variation. That makes STT easier, and for the same reason makes it a reasonable choice in voice anonymization. | |
| Mar 14, 2020 at 0:58 | comment | added | Jarrod Christman | @reo, depends on what threat you’re concerned about. If it’s a legal threat, I think you’d have a very good defense to discount the reconstructed voice as evidence. | |
| Mar 13, 2020 at 20:56 | comment | added | reo katoa | @JarrodChristman the goal is not to perfectly reverse the transformation, but to recover the voice "fingerprint" to enough fidelity that the speaker could be identified. This answer could be improved but makes a very good point that modern machine learning techniques (e.g. autoencoders) can very effectively reverse information-preserving transformations. The goal of an anonymizer, therefore, is to destroy the speaker-identifying information without destroying the ability of the listener to discern the linguistic content. | |
| Mar 13, 2020 at 16:28 | comment | added | Jarrod Christman | I would be curious as to this as well. Machine learning techniques, like neural networks, are composite functions trained over a data set. If you use obfuscation techniques that actually remove data, and potentially add some randomness into it, it can still be understood by people as a voice. However, if you were to try and train a NN to reconstruct the originally, it would have to guess and interpolate to try and recover the lost and random shifted data... this likely cannot be proved to be a 100% reversed version of the obfuscation, ever. | |
| Mar 13, 2020 at 9:05 | review | Low quality posts | |||
| Mar 13, 2020 at 19:15 | |||||
| Mar 13, 2020 at 7:41 | comment | added | schroeder♦ | 1. "Because magic (ML) might defeat it" is not an answer. 2. You have equated the kitten pic to voice anonymization but not proved or explained how they are in fact relatable. Can you explain or expand what you mean by "MFCC feature vectors" and "STT->TTS technologies"? These appear to be the actual valid points to your answer but you don't provide enough to be able to make sense of them. | |
| Mar 13, 2020 at 4:45 | review | First posts | |||
| Mar 13, 2020 at 7:25 | |||||
| Mar 13, 2020 at 4:42 | history | answered | P i | CC BY-SA 4.0 |