用凸优化提升低资源下语音识别的方言鲁棒性语言检测
Convex Low-resource Accent-Robust Language Detection in Speech Recognition
- 采用凸优化方法，通过多GPU ADMM加速训练
- 在低资源场景下实现97%-98%准确率，抗方言干扰强
- 适合语音系统开发与低资源语言研究者使用
全球化和多元文化持续催生更多样化的语音变体。然而，当前语音对话系统常因缺乏代表性方言和口音数据而失效，频繁误判输入语言，导致下游任务级联失败。在低资源条件下缓解方言差异仍是开放挑战，因标准微调计算成本高且易在高维语音数据上过拟合。本文提出凸语言检测（CLD）框架，将理论严谨的凸优化技术集成至语音对话系统流程中。该方法基于JAX实现多GPU交替方向乘子法（ADMM），保证全局最优并实现多项式时间快速训练。理论上，证明了凸目标函数可诱导认证的边界稳定性，并提供对特征扰动的保障。实验表明，该方法具备样本高效性和对输入方言变异的鲁棒性，在严苛低资源环境下达到97%-98%准确率。开源代码已发布于https://pypi.org/project/jaxcld/
原文摘要 · Abstract (English)
Globalization and multiculturalism continue to produce increasingly diverse speech varieties. Yet current spoken dialogue systems frequently fail on under-represented dialects and accents, often misidentifying the input language and causing cascading failures in downstream dialogue tasks. Addressing this dialectal variance under low-resource constraints remains an open challenge, as standard fine-tuning is computationally expensive and prone to overfitting on high-dimensional speech data. We propose Convex Language Detection (CLD), a novel framework that integrates theoretically grounded convex optimization techniques into the spoken dialogue systems pipeline. Our method is efficiently implemented via multi-GPU Alternating Direction Method of Multipliers (ADMM) in JAX, thus providing global optimality guarantees and fast training in polynomial time. Theoretically, we prove that our convex objective induces certified margin stability and provide guarantees against feature perturbations. Empirically, we demonstrate sample efficiency and robustness to input dialectical variation, achieving 97-98% accuracy in challenging low-resource regimes. Our open-source package is available at https://pypi.org/project/jaxcld/
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。