# MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates

arXiv: https://arxiv.org/abs/2603.23048 · HTML: https://mlsanity.com/paper/2603.23048/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [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)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [ICASSP 2023 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2303.11510/) (2023)
- [DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering](https://mlsanity.com/paper/2110.05588/) (2021)
- [Investigating self-supervised learning for speech enhancement and separation](https://mlsanity.com/paper/2203.07960/) (2022)
- [MaskSR: Masked Language Model for Full-band Speech Restoration](https://mlsanity.com/paper/2406.02092/) (2024)
- [Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction](https://mlsanity.com/paper/2310.02720/) (2023)
- [Self-Supervised Learning for speech recognition with Intermediate layer supervision](https://mlsanity.com/paper/2112.08778/) (2021)
- [Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2309.13860/) (2023)
- [An Adapter based Multi-label Pre-training for Speech Separation and Enhancement](https://mlsanity.com/paper/2211.06041/) (2022)
- [Sampling Frequency Independent Dialogue Separation](https://mlsanity.com/paper/2206.02124/) (2022)
- [Selective HuBERT: Self-Supervised Pre-Training for Target Speaker in Clean and Mixture Speech](https://mlsanity.com/paper/2311.04526/) (2023)
- [Progressive Residual Extraction based Pre-training for Speech Representation Learning](https://mlsanity.com/paper/2409.00387/) (2024)

## Abstract (arXiv)

Self-supervised learning (SSL) has advanced speech processing. However, existing speech SSL methods typically assume a single sampling rate and struggle with mixed-rate data due to temporal resolution mismatch. To address this limitation, we propose MSRHuBERT, a multi-sampling-rate adaptive pre-training method. Building on HuBERT, we replace its single-rate downsampling CNN with a multi-sampling-rate adaptive downsampling CNN that maps raw waveforms from different sampling rates to a shared temporal resolution without resampling. This design enables unified mixed-rate pre-training and fine-tuning. In experiments spanning 16 to 48 kHz, MSRHuBERT outperforms HuBERT on speech recognition and full-band speech reconstruction, preserving high-frequency detail while modeling low-frequency semantic structure. Moreover, MSRHuBERT retains HuBERT's mask-prediction objective and Transformer encoder, so existing analyses and improvements that were developed for HuBERT can apply directly.