US 2019/0295553 A1 · APPARATUS FOR RECOGNIZING VOICE SPEAKER AND METHOD FOR THE SAME

Abstract

Disclosed herein are an apparatus and method for recognizing a voice speaker. The apparatus for recognizing a voice speaker includes a voice feature extraction unit configured to extract a feature vector from a voice signal inputted through a microphone; and a speaker recognition unit configured to calculate a speaker recognition score by selecting a reverberant environment from multiple reverberant environment learning data sets based on the feature vector extracted by the voice feature extraction unit and to recognize a speaker by assigning a weight depending on the selected reverberant environment to the speaker recognition score.

Claims16

Dependent claims

An apparatus for recognizing a voice speaker, comprising:

a voice feature extraction unit configured to extract a feature vector from a voice signal inputted through a microphone;
and
a speaker recognition unit configured to calculate a speaker recognition score by selecting a reverberant environment from multiple reverberant environment learning data sets based on the feature vector extracted by the voice feature extraction unit and to recognize a speaker by assigning a weight depending on the selected reverberant environment to the speaker recognition score.

A method for recognizing a voice speaker, comprising:

receiving, by a voice feature extraction unit, a voice signal through a microphone;
extracting, by the voice feature extraction unit, a feature vector by extracting a characteristic signal from the voice signal;
estimating, by a speaker recognition unit, a reverberant environment having a high probability of being similar to the feature vector in multiple reverberant environment learning data sets;
selecting, by the speaker recognition unit, a model for recognizing a speaker from the estimated reverberant environment;
calculating, by the speaker recognition unit, a speaker recognition score using a selected reverberant environment model;
and
calculating, by the speaker recognition unit, a final speaker recognition score through a weighted combination of the calculated speaker recognition score and an estimated reverberant environment probability.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application

16/359,077Filed 20 Mar 2019

Priority

KR 10-2018-003253321 Mar 2018

Published

26 Sep 2019

Term ends

Not estimatedThe source records don’t support an estimate.

Classification9 codes

G10L 17/18
Speaker identification or verification techniques: artificial neural networks; Connectionist approaches
G06N 3/045
Architecture, e.g. interconnection topology: combinations of networks
G06N 3/047
Architecture, e.g. interconnection topology: probabilistic or stochastic networks
G06N 3/0499
Architecture, e.g. interconnection topology: feedforward networks

Apparatus for recognizing voice speaker and method for the same

Life of this patent

Apparatus for recognizing voice speaker and method for the same

Life of this patent

Abstract

Claims16