The method is based on the technology of universal hostility patches (UAP) created directly in the audio file. This digital “masking” makes the sound unrecognizable for automatic algorithms for identity and analysis, but does not distort the meaning of what is said and does not interfere with the perception of speech by a person.
The feature of the technology violates the work of algorithms responsible for issuing unique signs of the announcer. This allows you to protect the sound from experiments with unauthorized profile creation, voice fake creation and breaking biometry. At the same time, audio files are suitable for transcription, translation and other tasks that are not related to the definition of the speaker’s personality.
The new defense applies to those who regularly publish audio content, especially from teachers and speakers to lower reeds and video bloggers. It may also be useful for business and training platforms to protect hidden materials, including web seminars and internal courses.
Technology is suitable for files of any length from short copies to time performance. Development was accepted to be broadcasted at the International Interspeech 2025 Conference in Rotterdam and is already available in the public sphere.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
