# Improving Code-switching Language Modeling with Artificially Generated Texts using Cycle-consistent Adversarial Networks

arXiv: https://arxiv.org/abs/2112.06327 · HTML: https://mlsanity.com/paper/2112.06327/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 12 Dec 2021.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1711.11293/) (2017)
- [Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation](https://mlsanity.com/paper/1811.02356/) (2018)
- [An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation](https://mlsanity.com/paper/1808.08795/) (2018)
- [Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech](https://mlsanity.com/paper/1807.10945/) (2018)
- [Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling](https://mlsanity.com/paper/1810.10254/) (2018)

## Built on by (most cited first, 9 of 9)

- [The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges](https://mlsanity.com/paper/2212.09660/) (2022)
- [Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2205.06445/) (2022)
- [Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation](https://mlsanity.com/paper/2205.12649/) (2022)
- [Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition](https://mlsanity.com/paper/2207.04176/) (2022)
- [Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review](https://mlsanity.com/paper/2507.07741/) (2025)
- [Data Augmentation Techniques for Machine Translation of Code-Switched Texts: A Comparative Study](https://mlsanity.com/paper/2310.15262/) (2023)
- [Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation](https://mlsanity.com/paper/2306.08588/) (2023)
- [Romanization Encoding For Multilingual ASR](https://mlsanity.com/paper/2407.04368/) (2024)
- [The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR](https://mlsanity.com/paper/2503.23576/) (2025)

## Abstract (arXiv)

This paper presents our latest effort on improving Code-switching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a cycle-consistent adversarial networks based framework to transfer monolingual text into Code-switching text, considering Code-switching as a speaking style. Our experimental results on the SEAME corpus show that utilising artificially generated Code-switching text data improves consistently the language model as well as the automatic speech recognition performance.