Generating expressive speech audio from text data
US12033611B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 28, 2022 |
| Grant date | Jul 9, 2024 |
| Priority date | — |
| Expiry date | Aug 10, 2042 |
Classification
- Technology area (CPC A)Human Necessities
- CPC primaryA63F2300/6018
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system for use in video game development to generate expressive speech audio comprises a user interface configured to receive user-input text data and a user selection of a speech style. The system includes a machine-learned synthesizer comprising a text encoder, a speech style encoder and a decoder. The machine-learned synthesizer is configured to generate one or more text encodings derived from the user-input text data, using the text encoder of the machine-learned synthesizer; generate a speech style encoding by processing a set of speech style features associated with the selected speech style using the speech style encoder of the machine-learned synthesizer; combine the one or more text encodings and the speech style encoding to generate one or more combined encodings; and decode the one or more combined encodings with the decoder of the machine-learned synthesizer to generate predicted acoustic features. The system includes one or more modules configured to process the predicted acoustic features, the one or more modules comprising a machine-learned vocoder configured to generate a waveform of the expressive speech audio.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.