Fact · Languages and accents
Milde and Köhn say that compounds unknown to the language model are quite frequent in German, because German is a very productive language.
Checked against its source on October 17, 2026
In the source's own words
“As German is a very productive language, compounds unknown to the language model are quite frequent”
Open Source Automatic Speech Recognition for German, Benjamin Milde and Arne Köhn, arXiv (Computation and Language), 2018, Section 3.1, error analysis.
Open the original- What it measures
- The authors name compounding as the largest problem the model faced in their evaluation.
- What it does not show
- One 2018 system and two datasets. Newer models do better, but the same vocabulary problem remains.