# Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages

arXiv: https://arxiv.org/abs/2604.18204 · HTML: https://mlsanity.com/paper/2604.18204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 20 Apr 2026.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Simple and Effective Zero-shot Cross-lingual Phoneme Recognition](https://mlsanity.com/paper/2109.11680/) (2021)
- [ASR2K: Speech Recognition for Around 2000 Languages without Audio](https://mlsanity.com/paper/2209.02842/) (2022)
- [Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision](https://mlsanity.com/paper/2406.02166/) (2024)
- [Universal Automatic Phonetic Transcription into the International Phonetic Alphabet](https://mlsanity.com/paper/2308.03917/) (2023)
- [OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia](https://mlsanity.com/paper/2501.13306/) (2025)
- [Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages](https://mlsanity.com/paper/2508.05149/) (2025)
- [Frequency effects in Linear Discriminative Learning](https://mlsanity.com/paper/2306.11044/) (2023)
- [Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages](https://mlsanity.com/paper/2506.17459/) (2025)
- [Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties](https://mlsanity.com/paper/2104.01624/) (2021)
- [In-context Language Learning for Endangered Languages in Speech Recognition](https://mlsanity.com/paper/2505.20445/) (2025)

## Built on by (most cited first, 2 of 2)

- [Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation](https://mlsanity.com/paper/2608.28508/) (2026)
- [Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR](https://mlsanity.com/paper/2610.13807/) (2026)

## Abstract (arXiv)

We present a phoneme-level analysis of automatic speech recognition (ASR) for two low-resourced and phonologically complex East Caucasian languages, Archi and Rutul, based on curated and standardized speech-transcript resources totaling approximately 50 minutes and 1 hour 20 minutes of audio, respectively. Existing recordings and transcriptions are consolidated and processed into a form suitable for ASR training and evaluation. We evaluate several state-of-the-art audio and audio-language models, including wav2vec2, Whisper, and Qwen2-Audio. For wav2vec2, we introduce a language-specific phoneme vocabulary with heuristic output-layer initialization, which yields consistent improvements and achieves performance comparable to or exceeding Whisper in these extremely low-resource settings. Beyond standard word and character error rates, we conduct a detailed phoneme-level error analysis. We find that phoneme recognition accuracy strongly correlates with training frequency, exhibiting a characteristic sigmoid-shaped learning curve. For Archi, this relationship partially breaks for Whisper, pointing to model-specific generalization effects beyond what is predicted by training frequency. Overall, our results indicate that many errors attributed to phonological complexity are better explained by data scarcity. These findings demonstrate the value of phoneme-level evaluation for understanding ASR behavior in low-resource, typologically complex languages.