Tuplemax Loss for Language Identification

11/29/2018

∙

by   Li Wan, et al.

∙

0

∙

share

In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages. We want to model such prior knowledge into the way we train our neural networks, by replacing the commonly used softmax loss function with a novel loss function named tuplemax loss. As a matter of fact, a typical language identification system launched in North America has about 95 who could speak no more than two languages. Using the tuplemax loss, our system achieved a 2.33 3.85