Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean

arXiv:2606.26618 · cs.CL · Submitted 2026-06-25 · Read on arXiv

cs.CL

Submitted: 2026-06-25

Updated: 2026-09-24

Terminology

• Adaptation — 18× in this paper · explained in 1 episode
• Fine-Tuning — 12× in this paper · explained in 5 episodes
• LoRA Fine-Tuning — 3× in this paper · explained in 3 episodes
• Low-Resource Languages — 3× in this paper · explained in 4 episodes
• Parameter-Efficient Fine-Tuning — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Korean Single Speaker — 2× in this paper
• Low-Rank Adaptation (LoRA) — 2× in this paper · explained in 9 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Khmer Mean Opinion Score — 1× in this paper
• LoRA Adaptation — 1× in this paper · explained in 2 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Normalizing Flow — 1× in this paper · explained in 3 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes

Sources

• Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
• VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
• VoxCPM2 Technical Report
• Scaling Speech Technology to 1,000+ Languages
• Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning
• MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
• XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model
• Exploring Efficient-tuning Methods in Self-supervised Speech Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering