# Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data

arXiv: https://arxiv.org/abs/1904.03802 · HTML: https://mlsanity.com/paper/1904.03802/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges](https://mlsanity.com/paper/2212.09660/) (2022)
- [Language-specific Characteristic Assistance for Code-switching Speech Recognition](https://mlsanity.com/paper/2206.14580/) (2022)
- [Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition](https://mlsanity.com/paper/2207.04176/) (2022)
- [A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English](https://mlsanity.com/paper/2108.01280/) (2021)
- [Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review](https://mlsanity.com/paper/2507.07741/) (2025)
- [Monolingual Recognizers Fusion for Code-switching Speech Recognition](https://mlsanity.com/paper/2211.01046/) (2022)

## Abstract (arXiv)

The lack of code-switch training data is one of the major concerns in the development of end-to-end code-switching automatic speech recognition (ASR) models. In this work, we propose a method to train an improved end-to-end code-switching ASR using only monolingual data. Our method encourages the distributions of output token embeddings of monolingual languages to be similar, and hence, promotes the ASR model to easily code-switch between languages. Specifically, we propose to use Jensen-Shannon divergence and cosine distance based constraints. The former will enforce output embeddings of monolingual languages to possess similar distributions, while the later simply brings the centroids of two distributions to be close to each other. Experimental results demonstrate high effectiveness of the proposed method, yielding up to 4.5% absolute mixed error rate improvement on Mandarin-English code-switching ASR task.