Patent · US Active

Method for creating a speech database for a target vocabulary in order to train a speech recognition system

US7844459B2 · kind B2 · utility

12Cited by

6References

21Claims

0Family size

Assignee

Siemens Aktiengesellschaft · DE

Inventors

Mark W. Budde · Arcadia, US
Tobias Schneider · Brechen, DE

Key dates

Filing date	Apr 24, 2001
Grant date	Nov 30, 2010
Priority date	—
Expiry date	Oct 21, 2026

Classification

Technology area (CPC G)Physics
CPC primaryG10L2015/0631
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

The words of the target vocabulary are composed of segments, which have one or more phonemes, whereby the segments are derived from a training text that is independent from the target vocabulary. The training text can be an arbitrary generic text.

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