Stochastic future context for speech processing
US12334055B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 18, 2021 |
| Grant date | Jun 17, 2025 |
| Priority date | — |
| Expiry date | Feb 22, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/26
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The amount of future context used in a speech processing application allows for tradeoffs between performance and the delay in providing results to users. Existing speech processing applications may be trained with a specified future context size and perform poorly when used in production with a different future context size. A speech processing application trained using a stochastic future context allows a trained neural network to be used in production with different amounts of future context. During an update step in training, a future-context size may be sampled from a probability distribution, used to mask a neural network, and compute an output of the masked neural network. The output may then be used to compute a loss value and update parameters of the neural network. The trained neural network may then be used in production with different amounts of future context to provide greater flexibility for production speech processing applications.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.