└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | # Speech Model Compression Papers
 2 | 
 3 | This repo presents a collection of recent papers related to speech model compression. Please feel free to suggest other papers!
 4 | 
 5 | ## 2023
 6 | 
 7 | - [[INTERSPEECH]()] [[arXiv](https://arxiv.org/abs/2306.01385)] Task-Agnostic Structured Pruning of Speech Representation Models
 8 | - [[INTERSPEECH]()] [[arXiv](https://arxiv.org/abs/2305.17651)] [[code](https://github.com/pyf98/DPHuBERT)] DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models
 9 | - [[ICASSP](https://ieeexplore.ieee.org/document/10094300)] [[arXiv](https://arxiv.org/abs/2209.05735)] Learning ASR pathways: A sparse multilingual ASR model
10 | - [[ICASSP](https://ieeexplore.ieee.org/document/10096662)] [[arXiv](https://arxiv.org/abs/2303.07624)] I3D: Transformer Architectures with Input-Dependent Dynamic Depth for Speech Recognition
11 | - [[ICASSP](https://ieeexplore.ieee.org/document/10095780)] [[arXiv](https://arxiv.org/abs/2302.14132)] Structured Pruning of Self-Supervised Pre-Trained Models for Speech Recognition and Understanding
12 | - [[ICASSP](https://ieeexplore.ieee.org/document/10095480)] [[arXiv](https://arxiv.org/abs/2302.09437)] RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness
13 | - [[ICASSP](https://ieeexplore.ieee.org/abstract/document/10096445)] [[arXiv](https://arxiv.org/abs/2302.12757)] Ensemble Knowledge Distillation of Self-Supervised Speech Models
14 | 
15 | 
16 | ## 2022
17 | 
18 | - [[SLT](https://ieeexplore.ieee.org/document/10022446)] [[arXiv](https://arxiv.org/abs/2207.11906)] Learning a Dual-Mode Speech Recognition Model via Self-Pruning
19 | - [[INTERSPEECH](https://www.isca-speech.org/archive/interspeech_2022/wang22t_interspeech)] [[arXiv](https://arxiv.org/abs/2203.15610)] [[code](https://github.com/mechanicalsea/lighthubert)] LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT
20 | - [[INTERSPEECH](https://www.isca-speech.org/archive/interspeech_2022/ashihara22_interspeech.html)] [[arXiv](https://arxiv.org/abs/2207.06867)] Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models
21 | - [[INTERSPEECH](https://www.isca-speech.org/archive/interspeech_2022/lee22p_interspeech.html)] [[arXiv](https://arxiv.org/abs/2207.00555)] [[code](https://github.com/glory20h/FitHuBERT)] FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning
22 | - [[ICASSP](https://ieeexplore.ieee.org/document/9747490)] [[arXiv](https://arxiv.org/abs/2110.01900)] [[code](https://github.com/s3prl/s3prl/tree/main/s3prl/upstream/distiller)] DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT 
23 | 
24 | ## 2021
25 | 
26 | - [[NeurIPS](https://proceedings.neurips.cc/paper/2021/hash/b17c0907e67d868b4e0feb43dbbe6f11-Abstract.html)] [[arXiv](https://arxiv.org/abs/2106.05933)] PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
27 | 


--------------------------------------------------------------------------------