1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Structured Sparse Attention For End-To-End Automatic Speech Recognition

Structured Sparse Attention For End-To-End Automatic Speech Recognition

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

The Softmax normalization function-based attention mechanism is often employed by End-to-End Automatic Speech Recognition (E2E ASR) models to tell the network where to focus within the input. However, this mechanism leads to the attention distribution bec

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

Purchase

Videos in this product

Structured Sparse Attention For End-To-End Automatic Speech Recognition

00:12:34

0 views

The Softmax normalization function-based attention mechanism is often employed by End-to-End Automatic Speech Recognition (E2E ASR) models to tell the network where to focus within the input. However, this mechanism leads to the attention distribution bec