arXiv cs.AI· Andoni Sudupe, Inma Hernaez, Ander Arriandiaga, Christoforos Souganidis, Ibon Saratxaga, Eva Navas·· 4 小时前AI 评分39
首个开源巴斯克语语音语言模型问世：基于 LLaMA-Omni 架构与 Latxa
Developing a Speech Language Model for Basque
AI 导读
研究者发布了首个开源巴斯克语语音语言模型，采用 LLaMA-Omni 架构，以 Latxa 模型为骨干，通过微调将巴斯克语能力迁移到语音模态。团队将英文 VoiceAssistant-400K 语料翻译成巴斯克语并用巴斯克语 TTS 合成音频，以缓解数据稀缺。评测中内容质量得分 3.86/5，语音可懂度 WER 为 9.94%，音频质量 UTMOS 达 3.07。
正文 · 原文
Abstract:Although the recent development of LLMs has paved the way for multi-modal interaction, minority languages face difficulties keeping pace. This work presents the first open Speech Language Model for Basque, designed for low-latency, end-to-end spoken interaction. Based on the LLaMA-Omni architecture, the system integrates a Latxa model as its backbone, transferring its Basque capabilities to the spoken modality by fine-tuning several modules. To address data scarcity, the English VoiceAssistant-400K corpus was translated into Basque, and the audio was synthesized using a Basque TTS. Evaluation results confirm the system's viability, achieving 3.86/5 in content quality, a 9.94% WER for spoken intelligibility, and a 3.07 UTMOS for audio quality. This work demonstrates that advanced spoken interaction systems can be developed using modular architectures and synthetic data even in low-resource languages.
| Comments: | IberSPEECH2026 - Jornadas en Tecnologias del Habla and Iberian SLTech Workshop Events |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2610.36911 [cs.CL] |
| (or arXiv:2610.36911v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36911 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andoni Sudupe [view email]
[v1]
Tue, 27 Oct 2026 09:40:42 UTC (16,655 KB)
来源：arXiv cs.AI · arxiv.org