Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929227750703104 |
|---|---|
| author | Shi, Jiatong Inaguma, Hirofumi Ma, Xutai Kulikov, Ilia Sun, Anna |
| author_facet | Shi, Jiatong Inaguma, Hirofumi Ma, Xutai Kulikov, Ilia Sun, Anna |
| contents | Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech signals. In contrast, this paper aims to incorporate multi-resolution information into speech self-supervised representation learning. We introduce a SSL model that leverages a hierarchical Transformer architecture, complemented by HuBERT-style masked prediction objectives, to process speech at multiple resolutions. Experimental results indicate that the proposed model not only achieves more efficient inference but also exhibits superior or comparable performance to the original HuBERT model over various tasks. Specifically, significant performance improvements over the original HuBERT have been observed in fine-tuning experiments on the LibriSpeech speech recognition benchmark as well as in evaluations using the Speech Universal PERformance Benchmark (SUPERB) and Multilingual SUPERB (ML-SUPERB). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_02720 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction Shi, Jiatong Inaguma, Hirofumi Ma, Xutai Kulikov, Ilia Sun, Anna Sound Audio and Speech Processing Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech signals. In contrast, this paper aims to incorporate multi-resolution information into speech self-supervised representation learning. We introduce a SSL model that leverages a hierarchical Transformer architecture, complemented by HuBERT-style masked prediction objectives, to process speech at multiple resolutions. Experimental results indicate that the proposed model not only achieves more efficient inference but also exhibits superior or comparable performance to the original HuBERT model over various tasks. Specifically, significant performance improvements over the original HuBERT have been observed in fine-tuning experiments on the LibriSpeech speech recognition benchmark as well as in evaluations using the Speech Universal PERformance Benchmark (SUPERB) and Multilingual SUPERB (ML-SUPERB). |
| title | Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2310.02720 |