用合成数据提升低资源语音模型性能，同时避免声音呆板化。
Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
- 分离语调与音色，恢复复杂语言的表达力
- 通过温度驱动自检，提升生成稳定性
- 实现老挝语零样本语音克隆，超越商用系统
语音语言模型（SLMs）通过跳过显式的音素转换流程，在语音合成中展现出巨大潜力。然而，低资源语言因标注语音数据稀缺，其效果受限。实践中，合成数据成为扩展此类模型的主要策略，可提供可靠的语音监督。本文揭示这一依赖带来根本性权衡——我们称之为稳定性-表达力差距：合成数据虽提升发音准确性，却逐步抑制语调多样性，导致表达力崩溃（合成侵蚀）。为此，提出两种自对齐框架：解耦引导的自对齐（DGSA）通过分离语调与音色，恢复复杂语言的表达力；在真实参考数据极度有限时，温度驱动自检（TDSC）通过自动探索与筛选实现生成稳定。该方法超越强大商业系统（如ElevenLabs和Gemini Pro），首次实现老挝语零样本语音克隆。
原文摘要 · Abstract (English)
Spoken Language Models (SLMs) have emerged as a promising paradigm for speech synthesis by bypassing explicit grapheme-to-phoneme pipelines. However, their effectiveness in low-resource languages remains fundamentally limited by the scarcity of transcribed speech. In practice, synthetic data has become the primary strategy for scaling SLMs in such settings, providing reliable phonetic supervision when real data is insufficient. In this work, we show that this reliance introduces a fundamental trade-off, which we term the Stability-Expressivity Gap: while synthetic data improves phonetic accuracy, it progressively suppresses prosodic variability, ultimately leading to a collapse of expressivity (Synthetic Erosion). To bridge this gap, we propose two self-alignment frameworks. Disentanglement-Guided Self-Alignment (DGSA) recovers expressivity for complex languages by exploiting prosody-timbre separation. For regimes where authentic references are exceptionally limited, Temperature-Driven Self-Critique (TDSC) stabilizes generation through automated exploration and filtering. Our approach outperforms strong commercial systems, including ElevenLabs and Gemini Pro, and enables the first zero-shot voice cloning capability for Lao.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。