mlsanityData to 7 Oct 2026

Data Augmentation for End-to-end Code-switching Speech Recognition

arXiv 2011.02160 ↗First posted 4 Nov 2020cs.CL eess.AScited by 20

Not on the map. Why?

Abstract (arXiv)

Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data augmentation. Specifically, they are audio splicing with the existing code-switching data, and TTS with new code-switching texts generated by word translation or word insertion. Our experiments on 200 hours Mandarin-English code-switching dataset show that all the three proposed approaches yield significant improvements on code-switching ASR individually. Moreover, all the proposed approaches can be combined with recent popular SpecAugment, and an addition gain can be obtained. WER is significantly reduced by relative 24.0% compared to the system without any data augmentation, and still relative 13.0% gain compared to the system with only SpecAugment

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 3; 2023: 3; 2024: 3; 2025: 5; 2026: 1.

20 papers.

Sort:

By area:

  1. 2021QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpuscited by 38
  2. 2022End-to-End Speech Translation for Code Switched Speechcited by 26
  3. 2021On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASRcited by 9
  4. 2021Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Modelscited by 9
  5. 2021Non-autoregressive Mandarin-English Code-switching Speech Recognitioncited by 8
  6. 2022Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognitioncited by 7
  7. 2023LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASRcited by 6
  8. 2024SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASRcited by 6
  9. 2022Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognitioncited by 5
  10. 2025Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Reviewcited by 4
  11. 2023Cross-Corpora Spoken Language Identification with Domain Diversification and Generalizationcited by 3
  12. 2024CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognitioncited by 3
8 more
  1. 2023Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentationcited by 2
  2. 2025SAGE: Spliced-Audio Generated Data for Enhancing Foundational Models in Low-Resource Arabic-English Code-Switched Speech Recognitioncited by 2
  3. 2025Adapting Language Balance in Code-Switching Speechcited by 2
  4. 2021Global Structure-Aware Drum Transcription Based on Self-Attention Mechanismscited by 1
  5. 2025AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASRcited by 1
  6. 2025Bayesian Low-Rank Factorization for Robust Model Adaptationcited by 1
  7. 2024Enhancing Code-switched Text-to-Speech Synthesis Capability in Large Language Models with only Monolingual Corporacited by 0
  8. 2026Adding Robust Code-Switching Capabilities to High Performance Multilingual ASRcited by 0