arXiv：cs.CL· Katsumi Ibaraki, David Chiang·· 13 小时前
误差率还不够：低资源 ASR 中数据增强的代价
Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR
AI 导读
一项在四种低资源语言和英语、五种数据规模上的研究发现，SpecAugment 的总体误差改善最可靠，但会增加声调和腭化错误；基于文本的增强方法则引入辅音插入错误，两者结合可互相抵消各自引入的错误。文本增强方法将词频拉平后使声调与腭化错误频率提高 37–38%，且组合增益超过各自增益之和，但这种超加性在 100 小时后消失，互补性仅限低资源场景。
正文
Abstract:Data augmentation is standard practice for low-resource automatic speech recognition (ASR), but its benefits are almost always reported as aggregate error rates, leaving open why and when a method helps. On four low-resource languages and English at five data sizes, we cross two augmentations that modify existing audio (speed perturbation and SpecAugment) with two that modify text transcriptions and synthesize audio from it. We analyze errors at the phoneme level and find that they help for complementary reasons. SpecAugment has the most reliable aggregate improvements, but increases tone and palatalization errors, whereas text-based methods introduce consonant insertions; in combination, each reduces the errors the other introduces. This complementarity is predictable. Tone and palatalization are each signaled by a single acoustic property and occur least frequently in training (lowest training exposure), and text-based methods that flatten word frequency raise their frequency by 37--38%, reversing those errors while further improving aggregate error. The improvement from combining the methods exceeds the sum of their individual improvements; the superadditivity vanishes by 100 hours, limiting the complementarity to the low-resource regime. Where specific error types matter, we recommend selecting augmentation by training exposure and acoustic properties, both measurable before any training.
| Comments: | 5 pages |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.13807 [cs.CL] |
| (or arXiv:2610.13807v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13807 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Katsumi Ibaraki [view email]
[v1]
Fri, 9 Oct 2026 16:19:43 UTC (43 KB)
来源：arXiv：cs.CL · arxiv.org