Smoothing Model Predictions Using Adversarial Training Procedures for Speech Based Emotion Recognition

ICASSP, pp. 4934-4938, 2018.

Cited by: 4|Bibtex|Views20|Links
EI

Abstract:

Training discriminative classifiers involves learning a conditional distribution $p(y_{i}vertpmb{x}_{i})$ , given a set of feature vectors $pmb{x}_{i}$ and the corresponding labels $y_{i}, i=1ldots N$ . For a classifier to be generalizable and not overfit to training data, the resulting conditional distribution $p(y_{i}vertpmb{x}_{i}...More

Code:

Data:

Your rating :
0

 

Tags
Comments