# Enhance Language Identification using Dual-mode Model with Knowledge Distillation

arXiv: https://arxiv.org/abs/2203.03218 · HTML: https://mlsanity.com/paper/2203.03218/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 7 Mar 2022.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition](https://mlsanity.com/paper/1907.00457/) (2019)
- [Utterance-level end-to-end language identification using attention-based CNN-BLSTM](https://mlsanity.com/paper/1902.07374/) (2019)
- [Tuplemax Loss for Language Identification](https://mlsanity.com/paper/1811.12290/) (2018)

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

- [Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization](https://mlsanity.com/paper/2302.05110/) (2023)

## Abstract (arXiv)

In this paper, we propose to employ a dual-mode framework on the x-vector self-attention (XSA-LID) model with knowledge distillation (KD) to enhance its language identification (LID) performance for both long and short utterances. The dual-mode XSA-LID model is trained by jointly optimizing both the full and short modes with their respective inputs being the full-length speech and its short clip extracted by a specific Boolean mask, and KD is applied to further boost the performance on short utterances. In addition, we investigate the impact of clip-wise linguistic variability and lexical integrity for LID by analyzing the variation of LID performance in terms of the lengths and positions of the mimicked speech clips. We evaluated our approach on the MLS14 data from the NIST 2017 LRE. With the 3~s random-location Boolean mask, our proposed method achieved 19.23%, 21.52% and 8.37% relative improvement in average cost compared with the XSA-LID model on 3s, 10s, and 30s speech, respectively.