Back to results
US 2022/0093116 A1Published application
Transformer with gaussian weighted self-attention for speech enhancement
AssigneeSamsung Electronics Co., Ltd.
InventorsJaeYoung KIM, Mostafa EL-KHAMY, Jungwon LEE
Life of this patent
Estimating the term…
Abstract
A method and system for providing Gaussian weighted self-attention for speech enhancement are herein provided. According to one embodiment, the method includes receiving an input noise signal, generating a score matrix based on the received input noise signal, and applying a Gaussian weighted function to the generated score matrix.
Claims20
A method for Gaussian weighted self-attention for speech enhancement, comprising:
- receiving an input noise signal;
- generating a score matrix based on the received input noise signal;
- and
- applying a Gaussian weighted function to the generated score matrix by compensating for a sign after a softmax function.
1 more element
(canceled)
A system for Gaussian weighted self-attention for speech enhancement, comprising:
- a memory;
- and
- a processor configured to:
- receive an input noise signal,
- generate a score matrix based on the received input noise signal, and
- apply a Gaussian weighted function to the generated score matrix by compensating for a sign after a softmax function.
3 more elements
(canceled)
Dependencies are inferred from the claim text.