# Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech Models

arXiv: https://arxiv.org/abs/2502.05837 · HTML: https://mlsanity.com/paper/2502.05837/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 9 Feb 2025.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT](https://mlsanity.com/paper/2110.01900/) (2021)
- [Cascaded encoders for unifying streaming and non-streaming ASR](https://mlsanity.com/paper/2010.14606/) (2020)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT](https://mlsanity.com/paper/2203.15610/) (2022)
- [Efficient Knowledge Distillation for RNN-Transducer Models](https://mlsanity.com/paper/2011.06110/) (2020)
- [DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models](https://mlsanity.com/paper/2305.17651/) (2023)
- [Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models](https://mlsanity.com/paper/2207.06867/) (2022)
- [Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition](https://mlsanity.com/paper/2210.00169/) (2022)
- [DeepTwist: Learning Model Compression via Occasional Weight Distortion](https://mlsanity.com/paper/1810.12823/) (2018)
- [On the compression of shallow non-causal ASR models using knowledge distillation and tied-and-reduced decoder for low-latency on-device speech recognition](https://mlsanity.com/paper/2312.09842/) (2023)

## Abstract (arXiv)

Traditionally, Knowledge Distillation (KD) is used for model compression, often leading to suboptimal performance. In this paper, we evaluate the impact of combining KD loss with alternative pruning techniques, including Low-Rank Factorization (LRF) and l0 regularization, on a conformer-based pre-trained network under the paradigm of Self-Supervised Learning (SSL). We also propose a strategy to jointly prune and train an RNN-T-based ASR model, demonstrating that this approach yields superior performance compared to pruning a pre-trained network first and then using it for ASR training. This approach led to a significant reduction in word error rate: l0 and KD combination achieves the best non-streaming performance, with a 8.9% Relative Word Error Rate (RWER) improvement over the baseline, while LRF and KD combination yields the best results for streaming ASR, improving RWER by 13.4%.