Fact · Transcription
The authors say that even when each language in a mix is well resourced, the shortage of annotated code-switched audio makes recognition harder.
Checked against its source on October 17, 2026
In the source's own words
“Although the constituent languages may be individually high-resource, the scarcity of annotated code-switching data further compounds these challenges.”
Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives, Hexin Liu et al., arXiv, 2025, Abstract.
Open the original- What it measures
- This is why a recognizer trained on each language separately can still struggle with a mixed sentence.
- What it does not show
- A preprint's statement from its abstract, not a measured result.