# Transducer-based language embedding for spoken language identification

arXiv: https://arxiv.org/abs/2204.03888 · HTML: https://mlsanity.com/paper/2204.03888/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [VoxLingua107: a Dataset for Spoken Language Recognition](https://mlsanity.com/paper/2011.12998/) (2020)
- [Exploring wav2vec 2.0 on speaker verification and language identification](https://mlsanity.com/paper/2012.06185/) (2020)
- [Deep Speaker: an End-to-End Neural Speaker Embedding System](https://mlsanity.com/paper/1705.02304/) (2017)
- [Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model](https://mlsanity.com/paper/1712.01541/) (2017)
- [E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition](https://mlsanity.com/paper/2106.08211/) (2021)
- [AP20-OLR Challenge: Three Tasks and Their Baselines](https://mlsanity.com/paper/2006.03473/) (2020)
- [AP19-OLR Challenge: Three Tasks and Their Baselines](https://mlsanity.com/paper/1907.07626/) (2019)
- [Two-stage Training for Chinese Dialect Recognition](https://mlsanity.com/paper/1908.02284/) (2019)
- [Additive Phoneme-aware Margin Softmax Loss for Language Recognition](https://mlsanity.com/paper/2106.12851/) (2021)

## Built on by (most cited first, 2 of 2)

- [A Compact End-to-End Model with Local and Global Context for Spoken Language Identification](https://mlsanity.com/paper/2210.15781/) (2022)
- [Generative linguistic representation for spoken language identification](https://mlsanity.com/paper/2312.10964/) (2023)

## Abstract (arXiv)

The acoustic and linguistic features are important cues for the spoken language identification (LID) task. Recent advanced LID systems mainly use acoustic features that lack the usage of explicit linguistic feature encoding. In this paper, we propose a novel transducer-based language embedding approach for LID tasks by integrating an RNN transducer model into a language embedding framework. Benefiting from the advantages of the RNN transducer's linguistic representation capability, the proposed method can exploit both phonetically-aware acoustic features and explicit linguistic features for LID tasks. Experiments were carried out on the large-scale multilingual LibriSpeech and VoxLingua107 datasets. Experimental results showed the proposed method significantly improves the performance on LID tasks with 12% to 59% and 16% to 24% relative improvement on in-domain and cross-domain datasets, respectively.