用地理信息控制低秩更新，高效实现方言语音识别
GLoRIA: Gated Low-Rank Interpretable Adaptation for Dialectal ASR
- 通过地理位置调控低秩矩阵的贡献，实现参数高效适配
- 在GCND数据集上优于全量微调和常规LoRA，仅更新10%参数
- 支持未见方言泛化，且适配过程可地理可视化
方言语音识别因区域差异大、标注数据少而困难。本文提出GLoRIA，一种参数高效的适配框架，利用坐标等元数据调控预训练编码器中的低秩更新。GLoRIA在每个前馈层注入低秩矩阵，通过门控MLP根据位置信息决定各秩-1分量的非负贡献。在GCND数据集上，其性能超越地理条件全微调、LoRA及专一/统一全微调方法，达到当前最优词错误率，同时仅更新不足10%参数。模型还能良好泛化至未见方言，包括外推场景，并支持可解释的地理空间可视化适配模式。结果表明，基于元数据的低秩适配是方言语音识别的有效、可解释且高效方案。
原文摘要 · Abstract (English)
Automatic Speech Recognition (ASR) in dialect-heavy settings remains challenging due to strong regional variation and limited labeled data. We propose GLoRIA, a parameter-efficient adaptation framework that leverages metadata (e.g., coordinates) to modulate low-rank updates in a pre-trained encoder. GLoRIA injects low-rank matrices into each feed-forward layer, with a gating MLP determining the non-negative contribution of each LoRA rank-1 component based on location metadata. On the GCND corpus, GLoRIA outperforms geo-conditioned full fine-tuning, LoRA, and both dialect-specific and unified full fine-tuning, achieving state-of-the-art word error rates while updating under 10% of parameters. GLoRIA also generalizes well to unseen dialects, including in extrapolation scenarios, and enables interpretable adaptation patterns that can be visualized geospatially. These results show metadata-gated low-rank adaptation is an effective, interpretable, and efficient solution for dialectal ASR.
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。