.png){kind=icon}
Return
Deep Normalization for Speaker Vectors
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2020.3039573.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks. However, one potential issue with this approach is that the speaker vectors derived from deep embedding models tend to be non-Gaussian for each individual speaker, and non-homogeneous for distributions of different speakers. These irregular distributions can seriously impact speaker recognition performance, especially with the popular PLDA scoring method, which assumes homogeneous Gaussian distribution. In this article, we argue that deep speaker vectors require deep normalization, and propose a deep normalization approach based on a novel discriminative normalization flow (DNF) model. We demonstrate the effectiveness of the proposed approach with experiments using the widely used SITW and CNCeleb corpora. In these experiments, the DNF-based normalization delivered substantial performance gains and also showed strong generalization capability in out-of-domain tests.
Keywords:
Training
Speaker recognition
Transforms
Task analysis
Covariance matrices
Probabilistic logic
Dimensionality reduction
Normalization flow
speaker embedding
speaker recognition
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
5.1
Papers:
2.6K
Citations:
1.1W
Organization
Cited Papers
.png){kind=icon}
ShareSaveA QoS-Aware Dual Crosspoint Queued Switch with Largest Weighted Occupancy First Scheduling Algorithm
PREAI
ShareSaveShareSaveShareSave
View more