Learning task-specific subspaces via interventional post-training of speech foundation models

arXiv cs.CL Papers

Summary

This paper proposes a post-training refinement approach using interventional contrastive learning to disentangle speech foundation model representations into separate content and speaker subspaces. The method shows improved out-of-domain speaker verification performance and evidence of successful separation.

arXiv:2606.17967v1 Announce Type: new Abstract: Speech foundation models, pre-trained on large corpora of unlabelled speech data, produce general-purpose representations which are useful across tasks. However, these representations encode information about salient speech variables in a distributed manner, while downstream speech tasks rely on only some of this variability. In this work, we propose a post-training refinement approach using interventional contrastive learning. By leveraging an interventional dataset and multi-part contrastive loss, we learn a transformation from the entangled representation space of speech foundation models into separate content and speaker subspaces. We evaluate the learnt representations on speaker verification and keyword spotting tasks, showing improved out-of-domain speaker verification performance and evidence that speaker and content information are separated across the learned subspaces.
Original Article
View Cached Full Text

Cached at: 06/17/26, 05:42 AM

# Learning task-specific subspaces via interventional post-training of speech foundation models
Source: [https://arxiv.org/abs/2606.17967](https://arxiv.org/abs/2606.17967)
[View PDF](https://arxiv.org/pdf/2606.17967)

> Abstract:Speech foundation models, pre\-trained on large corpora of unlabelled speech data, produce general\-purpose representations which are useful across tasks\. However, these representations encode information about salient speech variables in a distributed manner, while downstream speech tasks rely on only some of this variability\. In this work, we propose a post\-training refinement approach using interventional contrastive learning\. By leveraging an interventional dataset and multi\-part contrastive loss, we learn a transformation from the entangled representation space of speech foundation models into separate content and speaker subspaces\. We evaluate the learnt representations on speaker verification and keyword spotting tasks, showing improved out\-of\-domain speaker verification performance and evidence that speaker and content information are separated across the learned subspaces\.

## Submission history

From: Jack Cox \[[view email](https://arxiv.org/show-email/8f301d11/2606.17967)\] **\[v1\]**Tue, 16 Jun 2026 14:18:20 UTC \(39 KB\)

Similar Articles

Selective Capability Unlearning in End-to-End Spoken Language Understanding

arXiv cs.CL

Proposes BindingSubspace (BSU), a representation-level framework that isolates and attenuates intent-conditioned directions in end-to-end spoken language understanding models to prevent capability persistence, where suppressing an intent still allows slot generation under forced prefixes. The method reduces forced-prefix recoverability while preserving retained performance on SLU benchmarks.