Patent · US Active

Optimizations to decoding of WFST models for automatic speech recognition

US9672810B2 · kind B2 · utility

3Cited by

13References

8Claims

0Family size

Assignee

Intel Corporation · US

Inventors

Joachim Hofer · Munich, DE
Georg Stemmer · Munich, DE

Key dates

Filing date	Sep 26, 2014
Grant date	Jun 6, 2017
Priority date	—
Expiry date	Jan 7, 2035

Classification

Technology area (CPC G)Physics
CPC primaryG10L2015/0635
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method in a computing device for decoding a weighted finite state transducer (WFST) for automatic speech recognition is described. The method includes sorting a set of one or more WFST arcs based on their arc weight in ascending order. The method further includes iterating through each arc in the sorted set of arcs according to the ascending order until the score of the generated token corresponding to an arc exceeds a score threshold. The method further includes discarding any remaining arcs in the set of arcs that have yet to be considered.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.