# Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study

arXiv: https://arxiv.org/abs/2603.02285 · HTML: https://mlsanity.com/paper/2603.02285/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [Towards End-to-end Unsupervised Speech Recognition](https://mlsanity.com/paper/2204.02492/) (2022)
- [Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings](https://mlsanity.com/paper/1804.00316/) (2018)
- [Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching](https://mlsanity.com/paper/1812.09323/) (2018)
- [Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models](https://mlsanity.com/paper/1904.04100/) (2019)
- [Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching](https://mlsanity.com/paper/2310.02382/) (2023)
- [A Theory of Unsupervised Speech Recognition](https://mlsanity.com/paper/2306.07926/) (2023)
- [Classification Error Bound for Low Bayes Error Conditions in Machine Learning](https://mlsanity.com/paper/2501.15977/) (2025)

## Abstract (arXiv)

Unsupervised speech recognition is a task of training a speech recognition model with unpaired data. To determine when and how unsupervised speech recognition can succeed, and how classification error relates to candidate training objectives, we develop a theoretical framework for unsupervised speech recognition grounded in classification error bounds. We introduce two conditions under which unsupervised speech recognition is possible. The necessity of these conditions are also discussed. Under these conditions, we derive a classification error bound for unsupervised speech recognition and validate this bound in simulations. Motivated by this bound, we propose a single-stage sequence-level cross-entropy loss for unsupervised speech recognition.