US Patent Issued to Spotify on March 24 for "Text-to-speech synthesis method and system, a method of training a text-to-speech synthesis system, and a method of calculating an expressivity score" (British Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,586,561, issued on March 24, was assigned to Spotify AB (Stockholm).

"Text-to-speech synthesis method and system, a method of training a text-to-speech synthesis system, and a method of calculating an expressivity score" was invented by John Flynn (London) and Zeenat Qureshi (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving text and inputting the received text in a prediction network. The method further includes generating, using the prediction network, speech data. The prediction network comprises a neural network that is trained to generate expressive speech data from text. The neural network is trained by: receiving ...