Trigger word detection using neural network waveform processing
US10847137B1 · kind B1 · utility
67Cited by
3References
16Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 12, 2017 |
| Grant date | Nov 24, 2020 |
| Priority date | — |
| Expiry date | Mar 14, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/088
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An approach to speech recognition, and in particular trigger word detection, implements fixed feature extraction form waveform samples with a neural network (NN). For example, rather than computing Log Frequency Band Energies (LFBEs), a convolutional neural network is used. In some implementations, this NN waveform processing is combined with a trained secondary classification that makes use of phonetic segmentation of a possible trigger word occurrence.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.