Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917308209823744 |
|---|---|
| author | Yang, Zijian Barkoczi, Jörg Schlüter, Ralf Ney, Hermann |
| author_facet | Yang, Zijian Barkoczi, Jörg Schlüter, Ralf Ney, Hermann |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02285 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study Yang, Zijian Barkoczi, Jörg Schlüter, Ralf Ney, Hermann Sound Machine Learning Audio and Speech Processing 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. |
| title | Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.02285 |