Fine-tuning XTTS-v2 on about 5,000 hours of weakly labeled Swiss podcast audio produces a voice adaptation model that renders Standard German text in seven Swiss German dialect regions with near-reference quality in human and automated tests.
The training and test sets were pre- partitioned by the dataset authors to ensure speaker indepen- dence, such that no speaker or sample appears in both splits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Voice Adaptation for Swiss German
Fine-tuning XTTS-v2 on about 5,000 hours of weakly labeled Swiss podcast audio produces a voice adaptation model that renders Standard German text in seven Swiss German dialect regions with near-reference quality in human and automated tests.