# Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers

arXiv: https://arxiv.org/abs/2506.21712 · HTML: https://mlsanity.com/paper/2506.21712/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 25 of 25)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [Exploring wav2vec 2.0 on speaker verification and language identification](https://mlsanity.com/paper/2012.06185/) (2020)
- [A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding](https://mlsanity.com/paper/2111.02735/) (2021)
- [Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification](https://mlsanity.com/paper/2110.05777/) (2021)
- [DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization](https://mlsanity.com/paper/2012.06659/) (2020)
- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning](https://mlsanity.com/paper/2305.10005/) (2023)
- [Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration](https://mlsanity.com/paper/2306.06232/) (2023)
- [MelHuBERT: A simplified HuBERT on Mel spectrograms](https://mlsanity.com/paper/2211.09944/) (2022)
- [Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations](https://mlsanity.com/paper/2406.09200/) (2024)
- [Information-Theoretic Understanding of Population Risk Improvement with Model Compression](https://mlsanity.com/paper/1901.09421/) (2019)
- [Speaker Embedding Extraction with Phonetic Information](https://mlsanity.com/paper/1804.04862/) (2018)
- [What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis](https://mlsanity.com/paper/2107.00439/) (2021)
- [Property Neurons in Self-Supervised Speech Transformers](https://mlsanity.com/paper/2409.05910/) (2024)
- [Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models](https://mlsanity.com/paper/2406.02285/) (2024)

## Built on by (most cited first, 1 of 1)

- [How Contrastive Decoding Enhances Large Audio Language Models](https://mlsanity.com/paper/2603.09232/) (2026)

## Abstract (arXiv)

In recent years, the impact of self-supervised speech Transformers has extended to speaker-related applications. However, little research has explored how these models encode speaker information. In this work, we address this gap by identifying neurons in the feed-forward layers that are correlated with speaker information. Specifically, we analyze neurons associated with k-means clusters of self-supervised features and i-vectors. Our analysis reveals that these clusters correspond to broad phonetic and gender classes, making them suitable for identifying neurons that represent speakers. By protecting these neurons during pruning, we can significantly preserve performance on speaker-related task, demonstrating their crucial role in encoding speaker information.