# LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering

arXiv: https://arxiv.org/abs/2607.02763 · HTML: https://mlsanity.com/paper/2607.02763/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM](https://mlsanity.com/paper/2305.15255/) (2023)
- [An Embarrassingly Simple Approach for LLM with Strong ASR Capacity](https://mlsanity.com/paper/2402.08846/) (2024)
- [SLM: Bridge the thin gap between speech and text foundation models](https://mlsanity.com/paper/2310.00230/) (2023)
- [SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training](https://mlsanity.com/paper/2412.15649/) (2024)
- [End-to-end Spoken Conversational Question Answering: Task, Dataset and Model](https://mlsanity.com/paper/2204.14272/) (2022)
- [Towards Data Distillation for End-to-end Spoken Conversational Question Answering](https://mlsanity.com/paper/2010.08923/) (2020)
- [Deep Learning Based Assessment of Synthetic Speech Naturalness](https://mlsanity.com/paper/2104.11673/) (2021)
- [Self-supervised Dialogue Learning for Spoken Conversational Question Answering](https://mlsanity.com/paper/2106.02182/) (2021)
- [OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models](https://mlsanity.com/paper/2604.00688/) (2026)
- [Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward](https://mlsanity.com/paper/2411.03866/) (2024)
- [HeySQuAD: A Spoken Question Answering Dataset](https://mlsanity.com/paper/2304.13689/) (2023)
- [LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models](https://mlsanity.com/paper/2308.10390/) (2023)
- [SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering](https://mlsanity.com/paper/2401.13463/) (2024)
- [InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training](https://mlsanity.com/paper/2503.02769/) (2025)
- [Data Augmentation for Low-Resource Quechua ASR Improvement](https://mlsanity.com/paper/2207.06872/) (2022)
- [GSQA: An End-to-End Model for Generative Spoken Question Answering](https://mlsanity.com/paper/2312.09781/) (2023)
- [SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing](https://mlsanity.com/paper/2601.09385/) (2026)
- [Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages](https://mlsanity.com/paper/2508.05149/) (2025)
- [On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering](https://mlsanity.com/paper/2209.12944/) (2022)
- [On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition](https://mlsanity.com/paper/2407.21476/) (2024)

## Abstract (arXiv)

Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM methods in low-resource settings. This paper investigates whether text-to-speech (TTS) can provide task-specific training data for Luxembourgish SQA without requiring a large human-recorded QA corpus. Starting from existing text-based QA resources, we translate questions into Luxembourgish, synthesize spoken questions with multiple TTS systems, and pair them with textual answers. We train a parameter-efficient SLAM-style architecture that connects a frozen Whisper encoder to frozen multilingual LLM backends through a learned projector and LoRA adapters. We compare MMS-TTS, Qwen3-TTS, and OmniVoice variants, including single-source corpora of about 48k questions and a 4TTS multi-source mix of approximately 230k questions. Evaluation on LLAMA-LB-Test with two real Luxembourgish speaker conditions shows that multi-source and voice-design-based synthetic training configurations yield the strongest SQA performance. The results also show that no-reference TTS quality scores do not monotonically predict downstream QA performance, indicating that synthetic speech must be evaluated as task-specific training data rather than only as natural-sounding audio.