Spectrogram to waveform synthesis using convolutional networks
US11462209B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 27, 2019 |
| Grant date | Oct 4, 2022 |
| Priority date | — |
| Expiry date | Feb 21, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/30
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
For the problem of waveform synthesis from spectrograms, presented herein are embodiments of an efficient neural network architecture, based on transposed convolutions to achieve a high compute intensity and fast inference. In one or more embodiments, for training of the convolutional vocoder architecture, losses are used that are related to perceptual audio quality, as well as a GAN framework to guide with a critic that discerns unrealistic waveforms. While yielding a high-quality audio, embodiments of the model can achieve more than 500 times faster than real-time audio synthesis. Multi-head convolutional neural network (MCNN) embodiments for waveform synthesis from spectrograms are also disclosed. MCNN embodiments enable significantly better utilization of modern multi-core processors than commonly-used iterative algorithms like Griffin-Lim and yield very fast (more than 300× real-time) waveform synthesis. Embodiments herein yield high-quality speech synthesis, without any iterative algorithms or autoregression in computations.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.