# Tuplemax Loss for Language Identification

arXiv: https://arxiv.org/abs/1811.12290 · HTML: https://mlsanity.com/paper/1811.12290/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2018.

## Built on by (most cited first, 3 of 3)

- [Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification](https://mlsanity.com/paper/2209.06058/) (2022)
- [Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech](https://mlsanity.com/paper/2202.12163/) (2022)
- [Enhance Language Identification using Dual-mode Model with Knowledge Distillation](https://mlsanity.com/paper/2203.03218/) (2022)

## Abstract (arXiv)

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% users who could speak no more than two languages. Using the tuplemax loss, our system achieved a 2.33% error rate, which is a relative 39.4% improvement over the 3.85% error rate of standard softmax loss method.