MUMBAI, India, June 24 -- Intellectual Property India has published a patent application (202617063862 A) filed by Google LLC on May 20, 2026, for Generating Music Using Machine Learning Models.
Inventors include Zayats, Victoria; Murad, Noah Benjamin; Walker Iv, Daniel David; Padfield, Dirk Ryan; Ferrari, Melissa Lianna; and Chen, Feifan.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating outputs conditioned on inputs using machine learning models. In one aspect, a method comprises receiving an input that comprises at least (i) a music input audio signal representing music and (ii) a voice input audio signal representing a voice sample of a particular speaker; obtaining text data representing lyrics; obtaining a plurality of audio tokens; obtaining a plurality of text tokens; obtaining an output audio signal representing music by providing a model input comprising at least the plurality of audio tokens and the plurality of text tokens as input to a machine learning model; and providing the output audio signal generated by the machine learning model that represents music of the input audio signal that includes the lyrics sung by the particular speaker.
Disclaimer: Curated by HT Syndication.
