---
title: "LuxEmo：卢森堡语表达性文本转语音情感语料库"
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","情感语料库","文本转语音"]
---

# LuxEmo：卢森堡语表达性文本转语音情感语料库

## 速览

LuxEmo 是一个 21 小时的卢森堡语对话式表达性语音语料库，包含 4 种情感类别。数据来源于 RTL 青年广播节目，采用自动检测结合人工验证的半自动策展流程，涵盖语音活动检测、降噪、语言识别、ASR 分割、情感预测等步骤。研究同时对比了五种基于德语跨语言迁移、多语言支持、卢森堡语适配及非参数韵律迁移的 TTS 系统。实验通过客观指标和人工评价评估性能。

## 关键点

- 首个卢森堡语情感语音数据集，21 小时、4 类情感。
- 半自动策展工作流集成多种检测与人工审核。
- 对比五种 TTS 方法，涵盖跨语言、多语言、领域适配和非参数韵律迁移。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_07ea5780fa8ed13dcfb0f413