Voice Adaptation for Swiss German
Not on the map. Why?
Abstract (arXiv)
This work investigates the performance of Voice Adaptation models for Swiss German dialects, i.e., translating Standard German text to Swiss German dialect speech. For this, we preprocess a large dataset of Swiss podcasts, which we automatically transcribe and annotate with dialect classes, yielding approximately 5000 hours of weakly labeled training material. We fine-tune the XTTSv2 model on this dataset and show that it achieves good scores in human and automated evaluations and can correctly render the desired dialect. Our work shows a step towards adapting Voice Cloning technology to underrepresented languages. The resulting model achieves CMOS scores of up to -0.28 and SMOS scores of 3.8.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 22 references that are in the map. First posted on arXiv 28 May 2025.
Builds on
18 of 22 references.
References · 18
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
- 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
- 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
- 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
- 2023Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modelingcited by 167
- 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 122
- 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 111
- 2023Libriheavy: a 50,000 hours ASR corpus with punctuation casing and contextcited by 85
- 2021Simple and Effective Zero-shot Cross-lingual Phoneme Recognitioncited by 79
- 2024WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmarkcited by 40
- 2021SwissDial: Parallel Multidialectal Corpus of Spoken Swiss Germancited by 26
6 more
- 2022SDS-200: A Swiss German Speech to Standard German Text Corpuscited by 22
- 2024ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddingscited by 22
- 2023STT4SG-350: A Speech Corpus for All Swiss German Dialect Regionscited by 18
- 2023AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Datacited by 16
- 2024Fine-tuning Whisper on Low-Resource Languages for Real-World Applicationscited by 11
- 2023Dialect Transfer for Swiss German Speech Translationcited by 7
Built on by
Not cited yet.