Query Expansion System for the VoxCeleb Speaker Recognition Challenge 2020
Yu-Sen Cheng, Chun-Liang Shih, Tien-Hong Lo, Wen-Ting Tseng, Berlin, Chen
TL;DR
This paper presents a speaker recognition system for VoxCeleb Challenge 2020 that employs query expansion and combines x-vector with ResNet scores, achieving notable improvements over baselines.
Contribution
The paper introduces a novel query expansion method and combines multiple scoring techniques to enhance speaker verification performance.
Findings
Query expansion significantly improves verification accuracy.
Combining Kaldi x-vector with ResNet scores yields better results.
The system outperforms baseline methods in the VoxCeleb Challenge.
Abstract
In this report, we describe our submission to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020. Two approaches are adopted. One is to apply query expansion on speaker verification, which shows significant progress compared to baseline in the study. Another is to use Kaldi extract x-vector and to combine its Probabilistic Linear Discriminant Analysis (PLDA) score with ResNet score.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech Recognition and Synthesis · Natural Language Processing Techniques · Music and Audio Processing
MethodsBatch Normalization · 1x1 Convolution · Convolution · Average Pooling · Bottleneck Residual Block · Residual Connection · Max Pooling · *Communicated@Fast*How Do I Communicate to Expedia? · Residual Block · Kaiming Initialization