---
title: "LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2606.31947v1"
permalink: "https://feed.astralor.com/items/itm_07ea5780fa8ed13dcfb0f413"
published: "2026-06-30T16:53:15.000Z"
score: 53
channel: "ai"
tags: ["LuxEmo","RTL","Emotional Speech Corpus","Text-to-Speech"]
---

# LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish

## At a glance

LuxEmo is a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories, derived from RTL youth broadcasts via semi-automatic curation combining automated detection and human validation. The workflow includes VAD, denoising, language identification, ASR segmentation, emotion prediction, and lexical cues. Five expressive TTS systems (cross-lingual, multilingual, adaptation, non-parametric prosody transfer) are benchmarked using objective metrics and human evaluation.

## Key points

- First emotional speech dataset for Luxembourgish: 21 hours, 4 emotion categories.
- Semi-automatic curation workflow integrating multiple detection steps and human validation.
- Benchmarks five TTS approaches: cross-lingual, multilingual, adaptation, and non-parametric prosody transfer.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_07ea5780fa8ed13dcfb0f413