Sorry, you need to enable JavaScript to visit this website.

DEEP SPEAKER REPRESENTATION USING ORTHOGONAL DECOMPOSITION AND RECOMBINATION FOR SPEAKER VERIFICATION

Citation Author(s):
Insoo Kim, Kyuhong Kim, Jiwhan Kim, Changkyu Choi
Submitted by:
Insoo Kim
Last updated:
13 May 2019 - 2:29am
Document Type:
Poster
Document Year:
2019
Event:
Presenters Name:
Insoo Kim
Paper Code:
1161

Abstract 

Abstract: 

Speech signal contains intrinsic and extrinsic variations such as accent, emotion, dialect, phoneme, speaking manner, noise, music, and reverberation. Some of these variations are unnecessary and are unspecified factors of variation. These factors lead to increased variability in speaker representation. In this paper, we assume that unspecified factors of variation exist in speaker representations, and we attempt to minimize variability in speaker representation. The key idea is that a primal speaker representation can be decomposed into orthogonal vectors and these vectors are recombined by using deep neural networks (DNN) to reduce speaker representation variability, yielding performance improvement for speaker verification (SV). The experimental results show that our proposed approach produces a relative equal error rate (EER) reduction of 47.1% compared to the use of the same convolutional neural network (CNN) architecture on the VoxCeleb dataset. Furthermore, our proposed method provides significant improvement for short utterances.

up
0 users have voted:

Dataset Files

Poster_InsooKim.pdf

(570)