mlsanityData to 7 Oct 2026

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

arXiv 2112.06327 ↗First posted 12 Dec 2021cs.CLcited by 9

Not on the map. Why?

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 13 of its 29 references that are in the map. First posted on arXiv 12 Dec 2021.

Builds on

13 of 29 references.

References · 13

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  6. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  7. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  8. 2017Style Transfer in Text: Exploration and Evaluationcited by 145
  9. 2017Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networkscited by 30
  10. 2018Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentationcited by 26
  11. 2018An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generationcited by 17
  12. 2018Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speechcited by 12
1 more
  1. 2018Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modelingcited by 9

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 2; 2024: 1; 2025: 2.

9 papers.

  1. 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challengescited by 35
  2. 2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognitioncited by 16
  3. 2022Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentationcited by 9
  4. 2022Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognitioncited by 5
  5. 2025Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Reviewcited by 4
  6. 2023Data Augmentation Techniques for Machine Translation of Code-Switched Texts: A Comparative Studycited by 3
  7. 2023Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentationcited by 2
  8. 2024Romanization Encoding For Multilingual ASRcited by 1
  9. 2025The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASRcited by 1