Method and system for training language models to reduce recognition errors
US10176799B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 2, 2016 |
| Grant date | Jan 8, 2019 |
| Priority date | — |
| Expiry date | Feb 2, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and for training a language model to reduce recognition errors, wherein the language model is a recurrent neural network language model (RNNLM) by first acquiring training samples. An automatic speech recognition system (ASR) is applied to the training samples to produce recognized words and probabilites of the recognized words, and an N-best list is selected from the recognized words based on the probabilities. determining word errors using reference data for hypotheses in the N-best list. The hypotheses are rescored using the RNNLM. Then, we determine gradients for the hypotheses using the word errors and gradients for words in the hypotheses. Lastly, parameters of the RNNLM are updated using a sum of the gradients.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.