Patent · US Active

Combined learning method and apparatus using deepening neural network based feature enhancement and modified loss function for speaker recognition robust to noisy environments

US12067989B2 · kind B2 · utility

0Cited by

0References

14Claims

0Family size

Assignee

IUCF-HYU (INDUSTRY-UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY) · KR

Inventors

Joon Chang · Austin, US
Joonyoung Yang · Bucheon-si, KR

Key dates

Filing date	Mar 30, 2020
Grant date	Aug 20, 2024
Priority date	—
Expiry date	Mar 9, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG10L21/0208
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Presented are a combined learning method and device using a transformed loss function and feature enhancement based on a deep neural network for speaker recognition that is robust in a noisy environment. A combined learning method using a transformed loss function and feature enhancement based on a deep neural network, according to one embodiment, can comprise the steps of: learning a feature enhancement model based on a deep neural network; learning a speaker feature vector extraction model based on the deep neural network; connecting an output layer of the feature enhancement model with an input layer of the speaker feature vector extraction model; and considering the connected feature enhancement model and speaker feature vector extraction model as one mode and performing combined learning for additional learning.

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