Triplet Entropy Loss

Introduced by Merwe in Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems

The Triplet Entropy Loss (TEL) training method aims to leverage both the strengths of Cross Entropy Loss (CEL) and Triplet loss during the training process, assuming that it would lead to better generalization. The TEL method though does not contain a pre-training step, but trains simultaneously with both CEL and Triplet losses.

Source: Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Language Identification	1	33.33%
Spoken language identification	1	33.33%
Spoken Language Understanding	1	33.33%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Loss Functions