论文研究
arxiv.org ·
弥合低资源文本转语音的质量差距：面向高棉语和韩语的 VoxCPM2 LoRA 微调
该论文研究低资源语言 TTS 质量差距，基于 2.4B 参数、无分词器的 VoxCPM2 模型（MiniCPM-4 语言模型骨干加流匹配扩散解码器），构建 25.5 小时清洗后的共享语言标注语料，用单个零初始化 LoRA 适配器同时微调语言模型与解码器，训练起点与原始零样本模型一致。母语者听测显示，最佳适配器（rank 64）将高棉语 MOS 从 3.85 提升至 4.23，配对 Wilcoxon 检验显著。摘要未完整给出韩语结果及推理成本等细节。
AI推荐理由 arXiv 论文，来源可信、事实明确：提出用单个 LoRA 适配器同时微调 2.4B 参数的无分词器 TTS 模型 VoxCPM2（MiniCPM-4 语言模型骨干 + 流匹配扩散解码器），面向高棉语和韩语等低资源语言。具体新信息包括：构建 25.5 小时清洗后的共享语言标注语料，适配器零初始化以保持原始零样本起点，高棉语 MOS 从 3.85 提升至 4.23（rank 64），配对 Wilcoxon 检验显著。局限：摘要被截断，韩语结果、推理成本与泛化性未给出，且 MOS 为主观听测。对低资源 TTS 与 LoRA 微调有实际参考价值，但属学术增量而非范式突破。
72
正文
Computer Science > Computation and Language
arXiv:2606.26618 (cs)
[Submitted on 25 Jun 2026 (v1), last revised 24 Sep 2026 (this version, v2)]
Title:Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean
Authors:Phannet Pov, Hyun Woo Park, Voneat Pen, Sovandara Chhoun, Wan-Sup Cho, Saksonita Khoeurn
View a PDF of the paper titled Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean, by Phannet Pov and 5 other authors
View PDF
HTML (experimental)
Abstract:Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B parameter, tokenizer-free TTS model that joins a MiniCPM-4 language-model backbone with a flow-matching diffusion decoder. We build one shared, language-tagged corpus of 25.5 hours after cleaning and adapt VoxCPM2 with a single Low-Rank Adaptation (LoRA) adapter, trained on both languages at once and added to both the language model and the decoder. The adapter is zero-initialized, so training starts exactly at the original zero-shot model. In native-speaker listening tests, the Khmer Mean Opinion Score (MOS) rises from 3.85 to 4.23 with the best adapter, rank 64. This gain is highly significant under a paired Wilcoxon test with p
new
|
recent
| 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)