1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Multi-Resolution Multi-Head Attention In Deep Speaker Embedding

Multi-Resolution Multi-Head Attention In Deep Speaker Embedding

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Pooling is an essential component to capture long-term speaker characteristics for speaker recognition. This paper proposes simple but effective pooling methods to compute attentive weights for better temporal aggregation over the variable-length input sp

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Multi-Resolution Multi-Head Attention In Deep Speaker Embedding

00:11:50

0 views

Pooling is an essential component to capture long-term speaker characteristics for speaker recognition. This paper proposes simple but effective pooling methods to compute attentive weights for better temporal aggregation over the variable-length input sp