# Semi-supervised acoustic model training for five-lingual code-switched ASR

arXiv: https://arxiv.org/abs/1906.08647 · HTML: https://mlsanity.com/paper/1906.08647/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2019.

## 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)
- [Investigations on Speech Recognition Systems for Low-Resource Dialectal Arabic-English Code-Switching Speech](https://mlsanity.com/paper/2108.12881/) (2021)
- [Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review](https://mlsanity.com/paper/2507.07741/) (2025)
- [Unified Modeling of Multi-Domain Multi-Device ASR Systems](https://mlsanity.com/paper/2205.06655/) (2022)
- [Code-Switched Urdu ASR for Noisy Telephonic Environment using Data Centric Approach with Hybrid HMM and CNN-TDNN](https://mlsanity.com/paper/2307.12759/) (2023)
- [Enhancing Code-Switching Speech Recognition with LID-Based Collaborative Mixture of Experts Model](https://mlsanity.com/paper/2409.02050/) (2024)
- [Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition](https://mlsanity.com/paper/2106.07699/) (2021)
- [The evaluation of a code-switched Sepedi-English automatic speech recognition system](https://mlsanity.com/paper/2403.07947/) (2024)
- [From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages](https://mlsanity.com/paper/2607.01502/) (2026)

## Abstract (arXiv)

This paper presents recent progress in the acoustic modelling of under-resourced code-switched (CS) speech in multiple South African languages. We consider two approaches. The first constructs separate bilingual acoustic models corresponding to language pairs (English-isiZulu, English-isiXhosa, English-Setswana and English-Sesotho). The second constructs a single unified five-lingual acoustic model representing all the languages (English, isiZulu, isiXhosa, Setswana and Sesotho). For these two approaches we consider the effectiveness of semi-supervised training to increase the size of the very sparse acoustic training sets. Using approximately 11 hours of untranscribed speech, we show that both approaches benefit from semi-supervised training. The bilingual TDNN-F acoustic models also benefit from the addition of CNN layers (CNN-TDNN-F), while the five-lingual system does not show any significant improvement. Furthermore, because English is common to all language pairs in our data, it dominates when training a unified language model, leading to improved English ASR performance at the expense of the other languages. Nevertheless, the five-lingual model offers flexibility because it can process more than two languages simultaneously, and is therefore an attractive option as an automatic transcription system in a semi-supervised training pipeline.