# Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages

arXiv: https://arxiv.org/abs/2011.03118 · HTML: https://mlsanity.com/paper/2011.03118/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2020.

## Built on by (most cited first, 3 of 3)

- [Wake-Cough: cough spotting and cougher identification for personalised long-term cough monitoring](https://mlsanity.com/paper/2110.03771/) (2021)
- [An Overview of Indian Spoken Language Recognition from Machine Learning Perspective](https://mlsanity.com/paper/2212.03812/) (2022)
- [Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2510.01145/) (2025)

## Abstract (arXiv)

In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of annotated corpora in the languages of interest has always been a primary challenge when developing speech recognition systems for this severely under-resourced type of speech. Hence, it is worthwhile to investigate the potential of using speech corpora available for other better-resourced languages to improve speech recognition performance. To achieve this, we train a mBNF extractor using nine Southern Bantu languages that form part of the freely available multilingual NCHLT corpus. We append these mBNFs to the existing MFCCs, pitch features and i-vectors to train acoustic models for automatic speech recognition (ASR) in the target code-switched languages. Our results show that the inclusion of the mBNF features leads to clear performance improvements over a baseline trained without the mBNFs for code-switched English-isiZulu, English-isiXhosa, English-Sesotho and English-Setswana speech.