Universal acoustic modeling using neural mixture models
US11676006B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 16, 2019 |
| Grant date | Jun 13, 2023 |
| Priority date | — |
| Expiry date | Dec 2, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/32
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
According to some embodiments, a universal modeling system may include a plurality of domain expert models to each receive raw input data (e.g., a stream of audio frames containing speech utterances) and provide a domain expert output based on the raw input data. A neural mixture component may then generate a weight corresponding to each domain expert model based on information created by the plurality of domain expert models (e.g., hidden features and/or row convolution). The weights might be associated with, for example, constrained scalar numbers, unconstrained scaler numbers, vectors, matrices, etc. An output layer may provide a universal modeling system output (e.g., an automatic speech recognition result) based on each domain expert output after being multiplied by the corresponding weight for that domain expert model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.