Real-time speaker-dependent neural vocoder
US10770063B2 · kind B2 · utility
2Cited by
11References
17Claims
0Family size
Assignees
Inventors
Key dates
| Filing date | Aug 22, 2018 |
| Grant date | Sep 8, 2020 |
| Priority date | — |
| Expiry date | Mar 15, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/22
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques for a recursive deep-learning approach for performing speech synthesis using a repeatable structure that splits an input tensor into a left half and right half similar to the operation of the Fast Fourier Transform, performs a 1-D convolution on each respective half, performs a summation and then applies a post-processing function. The repeatable structure may be utilized in a series configuration to operate as a vocoder or perform other speech processing functions.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.