Patent · US Active

System and method of automatic speech recognition using parallel processing for weighted finite state transducer-based speech decoding

US10255911B2 · kind B2 · utility

4Cited by

4References

23Claims

0Family size

Assignee

Intel Corporation · US

Inventors

Lukasz Malinowski · Gdańsk, PL
Piotr Majcher · Straszyn, PL
Georg Stemmer · Munich, DE
Piotr Rozen · Gdańsk, PL
Joachim Hofer · Munich, DE
Josef Bauer · Munich, DE

Key dates

Filing date	Dec 17, 2014
Grant date	Apr 9, 2019
Priority date	—
Expiry date	Dec 17, 2034

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/34
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A computer-implemented method of speech recognition comprises forming a weighted finite state transducer (WFST) having nodes associated with states and interconnected by arcs, and to identify at least one word or word sequence hypothesis, identifying multiple sub-graphs on the WFST, each sub-graph having the same arrangement of multiple states and at least one arc, and propagating tokens in parallel through the sub-graphs, where each sub-graph is stored as a supertoken each having an array of tokens.

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