1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. T-Gsa: Transformer With Gaussian-Weighted Self-Attention For Speech Enhancement

T-Gsa: Transformer With Gaussian-Weighted Self-Attention For Speech Enhancement

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Transformer neural networks (TNN) demonstrated state-of-art performance on many natural language processing (NLP) tasks, replacing recurrent neural networks (RNNs), such as LSTMs or GRUs. However, TNNs did not perform well in speech enhancement, whose con

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

Purchase

Videos in this product

T-Gsa: Transformer With Gaussian-Weighted Self-Attention For Speech Enhancement

00:12:22

1 view

Transformer neural networks (TNN) demonstrated state-of-art performance on many natural language processing (NLP) tasks, replacing recurrent neural networks (RNNs), such as LSTMs or GRUs. However, TNNs did not perform well in speech enhancement, whose con