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

arXiv: https://arxiv.org/abs/2606.17967 · HTML: https://mlsanity.com/paper/2606.17967/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Interventional Causal Representation Learning](https://mlsanity.com/paper/2209.11924/) (2022)
- [CITRIS: Causal Identifiability from Temporal Intervened Sequences](https://mlsanity.com/paper/2202.03169/) (2022)
- [SONAR: Sentence-Level Multimodal and Language-Agnostic Representations](https://mlsanity.com/paper/2308.11466/) (2023)
- [Linear Causal Disentanglement via Interventions](https://mlsanity.com/paper/2211.16467/) (2022)
- [Identifiability Guarantees for Causal Disentanglement from Soft Interventions](https://mlsanity.com/paper/2307.06250/) (2023)
- [ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers](https://mlsanity.com/paper/2204.09224/) (2022)
- [Identifiability of latent-variable and structural-equation models: from linear to nonlinear](https://mlsanity.com/paper/2302.02672/) (2023)
- [Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning](https://mlsanity.com/paper/2303.16535/) (2023)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learning](https://mlsanity.com/paper/2012.07178/) (2020)
- [Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion](https://mlsanity.com/paper/2203.16705/) (2022)
- [Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models](https://mlsanity.com/paper/2210.16043/) (2022)
- [Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations](https://mlsanity.com/paper/2406.09200/) (2024)
- [Disentangled Feature Learning for Real-Time Neural Speech Coding](https://mlsanity.com/paper/2211.11960/) (2022)

## Abstract (arXiv)

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.