Realtime Transformation Of Voice For Privacy Protection

Patent Status

Patent Pending

Brief Description

The technology, known as Speech Articulatory Coding (SPARC), is a neural encoding-decoding framework for speech. It works by inferring articulatory features from audio and then synthesizing new speech from those features. The system effectively disentangles the speaker's identity from the speech's articulation, enabling accent-preserving voice conversion and providing a foundation for real-time voice privacy protection.

Suggested uses

• Real-time voice privacy protection in communication applications.

• Zero-shot voice conversion that preserves accents.

  Creation of intelligible and high-quality synthetic speech.

Advantages

• Effectively disentangles speaker embedding from articulations.

• Enables accent-preserving zero-shot voice conversion.

• Produces fully intelligible, high-quality synthesized speech.

• Generalizes to unseen speakers.

• Provides an intuitively interpretable and controllable control space for speech production.

Related Materials