发表机构
University of Notre Dame（圣母大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出DonorRank学习排序框架，用于低资源跨语言语音识别的源语言选择，在两大语族语料库上验证其能准确预测源语言排名，提升选择效果，还可分析源语言选择并识别实用迁移模式。
AI 中文摘要
低资源自动语音识别（ASR）通常依赖跨语言迁移，模型从高资源源语言适配而来。但对于低资源语言社区的自发语音，因语言变异、正字法惯例演变及资源分布不均，源语言选择仍具挑战性。本文提出DonorRank，一种用于预测零样本ASR有效源语言的学习排序框架。在印度语族和非洲语族的两个多语言语音语料库上评估DonorRank，其能准确预测源语言排名，相比基于遗传相似性或高资源语言的常见启发式方法，提升了源语言选择效果。除改进迁移外，研究表明DonorRank是分析源语言选择本身的通用框架，分析显示源语言集的构成决定了哪些语言线索对预测成功迁移有用，还识别出可为低资源场景多语言ASR提供实际指导的迁移模式。
英文摘要
Low-resource automatic speech recognition (ASR) commonly relies on cross-lingual transfer, where models are adapted from higher-resource donor languages. However, selecting donors remains challenging for spontaneous speech from under-resourced language communities, due to linguistic variation, evolving orthographic conventions, and uneven resource availability. We present DonorRank, a learning-to-rank framework for predicting effective donor languages for zero-shot ASR. We evaluate DonorRank on two multilingual speech corpora of Indic and African language families. It accurately predicts donor language rankings and improves donor selection over common heuristics based on genetic similarity or high-resource languages. Beyond improving transfer, we show how DonorRank is a general framework for analyzing donor language selection itself. Our analyses show that the composition of the donor set determines which linguistic cues are useful in predicting successful transfer. We also identify transfer patterns that provide practical guidance for multilingual ASR in low-resource settings.
Comments11 pages, 4 figures, 12 tables
