# Language ID Prediction from Speech Using Self-Attentive Pooling and 1D-Convolutions

arXiv: https://arxiv.org/abs/2104.11985 · HTML: https://mlsanity.com/paper/2104.11985/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 28 references that are in the map.
- First posted on arXiv 24 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends](https://mlsanity.com/paper/2001.00378/) (2020)
- [Attention-Based Models for Text-Dependent Speaker Verification](https://mlsanity.com/paper/1710.10470/) (2017)
- [Language Identification Using Deep Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1708.04811/) (2017)
- [Spoken Language Identification using ConvNets](https://mlsanity.com/paper/1910.04269/) (2019)
- [Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems](https://mlsanity.com/paper/2012.03775/) (2020)

## Built on by (most cited first, 1 of 1)

- [SIGTYP 2021 Shared Task: Robust Spoken Language Identification](https://mlsanity.com/paper/2106.03895/) (2021)

## Abstract (arXiv)

This memo describes NTR-TSU submission for SIGTYP 2021 Shared Task on predicting language IDs from speech. Spoken Language Identification (LID) is an important step in a multilingual Automated Speech Recognition (ASR) system pipeline. For many low-resource and endangered languages, only single-speaker recordings may be available, demanding a need for domain and speaker-invariant language ID systems. In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results for the language identification task.