Improving Speaker Verification in Noisy Environment Using DNN Classifier

Chung Tran Quang,Quang Minh Nguyen,Pham Ngoc Phuong,Quoc Truong Do

2021 RIVF International Conference on Computing and Communication Technologies (RIVF)（2021）

引用 0|浏览0

暂无评分

摘要

Speaker verification in noisy environments is still a challenging task. Previous studies have proposed speaker embeddings (x-vectors, ThinResNet) with classifier models (PLDA, cosine) to classify if an audio is spoken by a specific speaker. The verification process is defined in 3 steps: training an embedding extractor, enrollment and verification. Most studies were trying to mitigate the noisy is...

查看译文

关键词

Training,Computational modeling,Pipelines,Neural networks,Data models,Communications technology,Noise measurement

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要