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

Zikang Huang, Meng Ge, Tianrui Wang, Xuanchen Li, Xiaobao Wang +2 more
3/24/2026
cs.SDcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

AAT: Adapting Audio Transformer for Various Acoustics Recognition Tasks

83% match1 repo92024

Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition

81% match2024

Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting

80% match2024

Adapting Text LLMs to Speech via Multimodal Depth Up-Scaling

80% match2026

MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations

80% match2024

Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology

80% match1 repo22024

Cite this paper

@article{huang2026msrhubert,
  title  = {MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates},
  author = {Zikang Huang and Meng Ge and Tianrui Wang and Xuanchen Li and Xiaobao Wang and Longbiao Wang and Jianwu Dang},
  year   = {2026},
  eprint = {2603.23048},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.23048v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.23048.svg)](https://codeofpaper.com/paper/2603.23048)

Discussion