Patent · US Active

Modeling device and method for speaker recognition, and speaker recognition system

US9595260B2 · kind B2 · utility

3Cited by

5References

25Claims

0Family size

Assignee

Panasonic Intellectual Property Corporation of America · US

Inventors

Haifeng Shen · 余新镇, CN
Long Ma · Boulder, US
Bingqi Zhang · Beijing, CN

Key dates

Filing date	Dec 10, 2010
Grant date	Mar 14, 2017
Priority date	—
Expiry date	Jan 3, 2031

Classification

Technology area (CPC G)Physics
CPC primaryG10L17/04
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A modeling device comprises a front end which receives enrollment speech data from each target speaker, a reference anchor set generation unit which generates a reference anchor set using the enrollment speech data based on an anchor space, and a voice print generation unit which generates voice prints based on the reference anchor set and the enrollment speech data. By taking the enrollment speech and speaker adaptation technique into account, anchor models with a smaller size can be generated, so reliable and robust speaker recognition with a smaller size reference anchor set is possible.

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