.png){kind=icon}
返回
Xi-Vector Embedding for Speaker Recognition
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2021.3091932.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present a Bayesian formulation for deep speaker embedding, wherein the xi-vector is the Bayesian counterpart of the x-vector, taking into account the uncertainty estimate. On the technology front, we offer a simple and straightforward extension to the now widely used x-vector. It consists of an auxiliary neural net predicting the frame-wise uncertainty of the input sequence. We show that the proposed extension leads to substantial improvement across all operating points, with a significant reduction in error rates and detection cost. On the theoretical front, our proposal integrates the Bayesian formulation of linear Gaussian model to speaker-embedding neural networks via the pooling layer. In one sense, our proposal integrates the Bayesian formulation of the i-vector to that of the x-vector. Hence, we refer to the embedding as the xi-vector, which is pronounced as /zai/ vector. Experimental results on the SITW evaluation set show a consistent improvement of over 17.5% in equal-error-rate and 10.9% in minimum detection cost.
Keyword:
Speaker verification
neural embedding
uncertainty
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Genome-Wide Analysis and Exploration of WRKY Transcription Factor Family Involved in the Regulation of Shoot Branching in Petunia.png)
GenesOAAI
GenesIF0
OAAI分享收藏Increasing locomotor efficiency among North American ungulates across the Oligocene-Miocene boundary提高北美有蹄类动物在古新世-始新世界线时期的运动效率
PREAI
分享收藏分享收藏
查看更多内容