LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish
This work addresses the lack of expressive speech resources for low-resource languages like Luxembourgish, enabling research in expressive TTS for underrepresented languages.
LuxEmo introduces a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories, derived from RTL youth broadcasts via a semi-automatic curation workflow. Benchmarking five expressive TTS systems shows that cross-lingual transfer from German and multilingual approaches achieve competitive results, with non-parametric prosody transfer performing best in human evaluation.
State-of-the-art speech datasets predominantly focus on widely spoken languages, often overlooking low-resource languages such as Luxembourgish, which remain underrepresented in speech technology research. In this work, we introduce LuxEmo, a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories. LuxEmo is derived from Radio Télévision Luxembourg (RTL) youth broadcasts, using automated detection followed by human validation. We propose a semi-automatic curation workflow combining voice activity detection, denoising, language identification, LuxASR-based segmentation, automatic emotion prediction, lexical cues, and targeted human review. Additionally, we benchmark five expressive TTS systems covering German-based cross-lingual transfer, multilingual Luxembourgish support, Luxembourgish adaptation, and non-parametric prosody transfer. Performance is evaluated using both objective metrics and human evaluation.