Channel adversarial training for cross-channel text-independent speaker recognition

ICASSP, 2019.

Cited by: 6|Views19
EI

Abstract:

The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in real-world applications, mismatch always exists between these two datasets, which may severely deteriorate...More

Code:

Data:

Your rating :
0

 

Tags
Comments