US Patent Issued to SONY GROUP on March 31 for "Machine learning (ML) based emotion, identity and voice conversion in audio using virtual domain mixing and fake pair-masking" (Indian Inventors)

ALEXANDRIA, Va., March 31 -- United States Patent no. 12,592,242, issued on March 31, was assigned to SONY GROUP Corp. (Tokyo).

"Machine learning (ML) based emotion, identity and voice conversion in audio using virtual domain mixing and fake pair-masking" was invented by Nirmesh Shah (Bengaluru, India), Mayank Kumar Singh (Bengaluru, India), Naoya Takahashi (Bengaluru, India) and Naoyuki Onoe (Bengaluru, India).

According to the abstract* released by the U.S. Patent & Trademark Office: "An electronic device and method for machine learning (ML) based emotion and voice conversion in audio using virtual domain mixing and fake pair-masking is disclosed. The electronic device receives a source audio associated with a first user, a reference-sp...