# A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

arXiv: https://arxiv.org/abs/2011.03115 · HTML: https://mlsanity.com/paper/2011.03115/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge](https://mlsanity.com/paper/2210.15759/) (2022)
- [Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery](https://mlsanity.com/paper/2103.08199/) (2021)
- [Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition](https://mlsanity.com/paper/2201.11207/) (2022)
- [Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation](https://mlsanity.com/paper/2104.00994/) (2021)
- [Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings](https://mlsanity.com/paper/2106.04298/) (2021)
- [Bridging Gaps in Natural Language Processing for Yor`ub'a: A Systematic Review of a Decade of Progress and Prospects](https://mlsanity.com/paper/2502.17364/) (2025)
- [Learning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Network](https://mlsanity.com/paper/2207.14568/) (2022)
- [Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units](https://mlsanity.com/paper/2407.04652/) (2024)
- [Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery](https://mlsanity.com/paper/2105.01786/) (2021)

## Abstract (arXiv)

In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic subspace, and simultaneously specify the subspace itself as an embedding on a hyper-subspace. We train the hyper-subspace on a set of transcribed languages and transfer it to the target language. In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it. We conduct our experiments on TIMIT and two low-resource languages: Mboshi and Yoruba. Results show that our model outperforms major acoustic unit discovery techniques, both in terms of clustering quality and segmentation accuracy.