A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912610874556416 |
|---|---|
| author | Blaschke, Verena Winkler, Miriam Förster, Constantin Wenger-Glemser, Gabriele Plank, Barbara |
| author_facet | Blaschke, Verena Winkler, Miriam Förster, Constantin Wenger-Glemser, Gabriele Plank, Barbara |
| contents | Although Germany has a diverse landscape of dialects, they are underrepresented in current automatic speech recognition (ASR) research. To enable studies of how robust models are towards dialectal variation, we present Betthupferl, an evaluation dataset containing four hours of read speech in three dialect groups spoken in Southeast Germany (Franconian, Bavarian, Alemannic), and half an hour of Standard German speech. We provide both dialectal and Standard German transcriptions, and analyze the linguistic differences between them. We benchmark several multilingual state-of-the-art ASR models on speech translation into Standard German, and find differences between how much the output resembles the dialectal vs. standardized transcriptions. Qualitative error analyses of the best ASR model reveal that it sometimes normalizes grammatical differences, but often stays closer to the dialectal constructions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02894 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation Blaschke, Verena Winkler, Miriam Förster, Constantin Wenger-Glemser, Gabriele Plank, Barbara Computation and Language Audio and Speech Processing Although Germany has a diverse landscape of dialects, they are underrepresented in current automatic speech recognition (ASR) research. To enable studies of how robust models are towards dialectal variation, we present Betthupferl, an evaluation dataset containing four hours of read speech in three dialect groups spoken in Southeast Germany (Franconian, Bavarian, Alemannic), and half an hour of Standard German speech. We provide both dialectal and Standard German transcriptions, and analyze the linguistic differences between them. We benchmark several multilingual state-of-the-art ASR models on speech translation into Standard German, and find differences between how much the output resembles the dialectal vs. standardized transcriptions. Qualitative error analyses of the best ASR model reveal that it sometimes normalizes grammatical differences, but often stays closer to the dialectal constructions. |
| title | A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.02894 |