LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish

• URL: http://arxiv.org/abs/2606.31947v2
• Date: Thu, 02 Jul 2026 16:10:55 GMT
• Title: LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish
• Abstract summary: We introduce LuxEmo, a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories.<n>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.
• Score: 1.0590698823137754
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs [54.75016325571445]
  Speech Large Language Models (LLMs) show great promise for speech emotion recognition via generative interfaces.<n> shifting from closed-set to open text generation introduces zero-shotity, making evaluation highly sensitive to prompts.<n>We present VoxEmo, a comprehensive SER benchmark encompassing 35 emotion corpora across 15 languages for Speech LLMs.
  arXiv  Detail & Related papers  (2026-03-09T21:10:34Z)
• PRiSM: Benchmarking Phone Realization in Speech Models [70.82595415252682]
  Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis.<n>We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception.
  arXiv  Detail & Related papers  (2026-01-20T15:00:36Z)
• LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data [2.383798778903081]
  LuxIT is a novel, monolingual instruction tuning dataset for Luxembourgish developed to mitigate this challenge.<n>We synthesize the dataset from a corpus of native Luxembourgish texts, utilizing DeepSeek-R1-0528, chosen for its shown proficiency in Luxembourgish.
  arXiv  Detail & Related papers  (2025-10-28T14:02:55Z)
• Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study [59.30098850050971]
  This work evaluates LLM prompting-based detection across eight non-English languages.<n>We show that while zero-shot and few-shot prompting lag behind fine-tuned encoder models on most of the real-world evaluation sets, they achieve better generalization on functional tests for hate speech detection.
  arXiv  Detail & Related papers  (2025-05-09T16:00:01Z)
• Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy [7.59001382786429]
  This paper addresses the challenges in developing language models for less-represented languages, with a focus on Luxembourgish.<n>We propose a novel text generation model based on the T5 architecture, combining limited Luxembourgish data with equal amounts of German and French data.<n>For the evaluation, we introduce LuxGen, a text generation benchmark that is the first of its kind for Luxembourgish.
  arXiv  Detail & Related papers  (2024-12-12T16:23:12Z)
• LuxBank: The First Universal Dependency Treebank for Luxembourgish [0.38447712214412116]
  Luxembourgish is a West Germanic language spoken by approximately 400,000 people. We introduce LuxBank, the first Universal Dependencies (UD) Treebank for Luxembourgish.
  arXiv  Detail & Related papers  (2024-11-07T15:50:40Z)
• Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages [49.6922490267701]
  We introduce a new zero resource code-switched speech benchmark designed to assess the code-switching capabilities of self-supervised speech encoders. We showcase a baseline system of language modeling on discrete units to demonstrate how the code-switching abilities of speech encoders can be assessed.
  arXiv  Detail & Related papers  (2023-10-04T17:58:11Z)
• MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition [51.412413996510814]
  We propose MixSpeech, a cross-modality self-learning framework that utilizes audio speech to regularize the training of visual speech tasks. MixSpeech enhances speech translation in noisy environments, improving BLEU scores for four languages on AVMuST-TED by +1.4 to +4.2.
  arXiv  Detail & Related papers  (2023-03-09T14:58:29Z)
• Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling [92.55131711064935]
  We propose a cross-lingual neural language model, VALL-E X, for cross-lingual speech synthesis. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. It can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker's voice, emotion, and acoustic environment.
  arXiv  Detail & Related papers  (2023-03-07T14:31:55Z)
• MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition [12.23416994447554]
  We present a multi-lingual speech recognition network named Mixture-of-Language-Expert(MoLE) MoLE analyzes linguistic expression from input speech in arbitrary languages, activating a language-specific expert with a lightweight language tokenizer. Based on the reliability, the activated expert and the language-agnostic expert are aggregated to represent language-conditioned embedding.
  arXiv  Detail & Related papers  (2023-02-27T13:26:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.