Speech processing techniques
US12205574B1 · kind B1 · utility
0Cited by
1References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Mar 22, 2021 |
| Grant date | Jan 21, 2025 |
| Priority date | — |
| Expiry date | Apr 24, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/51
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques for using multiple machine learning (ML) models, with varying compute costs, for ASR processing is described. The system may include an arbitrator component configured to determine which ML model is to be used to process an audio frame from a sequence of audio frames representing a spoken natural language input. The arbitrator component may switch between the ML models, on a frame-by-frame basis, to reduce an overall compute cost for the entire spoken natural language input. The outputs of the different ML models may be combined to determine the final output for the entire spoken natural language input.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.