# Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR

arXiv: https://arxiv.org/abs/2610.13807 · HTML: https://mlsanity.com/paper/2610.13807/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 17 of 17)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding](https://mlsanity.com/paper/1807.01554/) (2018)
- [Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems](https://mlsanity.com/paper/1912.09257/) (2019)
- [Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation](https://mlsanity.com/paper/2305.10951/) (2023)
- [Pseudo-Labeling for Massively Multilingual Speech Recognition](https://mlsanity.com/paper/2111.00161/) (2021)
- [Voice Conversion Can Improve ASR in Very Low-Resource Settings](https://mlsanity.com/paper/2111.02674/) (2021)
- [Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap](https://mlsanity.com/paper/2410.16726/) (2024)
- [Data Augmentation for Low-Resource Quechua ASR Improvement](https://mlsanity.com/paper/2207.06872/) (2022)
- [Evaluating and reducing the distance between synthetic and real speech distributions](https://mlsanity.com/paper/2211.16049/) (2022)
- [When Is TTS Augmentation Through a Pivot Language Useful?](https://mlsanity.com/paper/2207.09889/) (2022)
- [Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation](https://mlsanity.com/paper/2208.12888/) (2022)
- [Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling](https://mlsanity.com/paper/2408.14026/) (2024)
- [Regularizing Learnable Feature Extraction for Automatic Speech Recognition](https://mlsanity.com/paper/2506.09804/) (2025)
- [Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages](https://mlsanity.com/paper/2604.18204/) (2026)

## Abstract (arXiv)

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.