Lattice decoding and result confirmation using recurrent neural networks
US10210862B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 6, 2016 |
| Grant date | Feb 19, 2019 |
| Priority date | — |
| Expiry date | Oct 1, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Neural networks may be used in certain automatic speech recognition systems. To improve performance at these neural networks, the present system converts the lattice into a matrix form, thus maintaining certain information included in the lattice that might otherwise be lost while also placing the lattice in a form that may be manipulated by other components to perform operations such as checking ASR results. The matrix representation of the lattice may be transformed into a vector representation by calculations performed at a recurrent neural network (RNN). By representing the lattice as a vector representation the system may perform additional operations, such as ASR results confirmation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.