Cross Attentive Pooling for Speaker Verification
2021 IEEE Spoken Language Technology Workshop (SLT)(2021)
摘要
The goal of this paper is text-independent speaker verification where utterances come from `in the wild' videos and may contain irrelevant signal. While speaker verification is naturally a pair-wise problem, existing methods to produce the speaker embeddings are instance-wise. In this paper, we propose Cross Attentive Pooling (CAP) that utilises the context information across the reference-query pair to generate utterance-level embeddings that contain the most discriminative information for the pair-wise matching problem. Experiments are performed on the VoxCeleb dataset in which our method outperforms comparable pooling strategies.
更多查看译文
关键词
speaker recognition,speaker verification,cross attention
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