# Pretrained self-supervised speech models can recognize unseen consonants

arXiv: https://arxiv.org/abs/2606.11542 · HTML: https://mlsanity.com/paper/2606.11542/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages](https://mlsanity.com/paper/2511.09690/) (2025)
- [Do self-supervised speech models develop human-like perception biases?](https://mlsanity.com/paper/2205.15819/) (2022)
- [Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages](https://mlsanity.com/paper/2305.12606/) (2023)
- [Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't](https://mlsanity.com/paper/2406.09202/) (2024)
- [On the Cross-lingual Transferability of Pre-trained wav2vec2-based Models](https://mlsanity.com/paper/2511.21704/) (2025)

## Abstract (arXiv)

Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations. However, their training data are heavily skewed toward high-resource languages with little data from low-resource languages, raising concerns about the potential underrepresentation of typologically uncommon speech sounds such as click consonants primarily found in Khoisan languages. This leads to our central research question: Can these models recognize click consonants as accurately as other speech sounds? To address this question, we fine-tune and compare pretrained self-supervised speech models (Wav2Vec2 and HuBERT) on data from two click-rich Khoisan languages (G|ui and West !Xoon). Our results reveal that the fine-tuned models consistently recognize clicks more accurately than non-clicks, suggesting that self-supervision enables generalization across human speech sounds including rare phonemes.