MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914417439932416 |
|---|---|
| author | Huang, Zikang Ge, Meng Wang, Tianrui Li, Xuanchen Wang, Xiaobao Wang, Longbiao Dang, Jianwu |
| author_facet | Huang, Zikang Ge, Meng Wang, Tianrui Li, Xuanchen Wang, Xiaobao Wang, Longbiao Dang, Jianwu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23048 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates Huang, Zikang Ge, Meng Wang, Tianrui Li, Xuanchen Wang, Xiaobao Wang, Longbiao Dang, Jianwu Sound Artificial Intelligence 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. |
| title | MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2603.23048 |