Ac-mix: Self-supervised Adaptation For Low-resource Automatic Speech Recognition Using Agnostic Contrastive Mixup
2024 · Carlos Carvalho, Alberto Abad
Abstract
Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for fine-tuning. Despite the advances in SSL, a significant challenge remains when the data used for pre-training (source domain) mismatches the fine-tuning data (target domain). To tackle this domain mismatch challenge, we propose a new domain adaptation method for low-resource ASR focused on contrastive mixup for joint-embedding architectures named AC-Mix (agnostic contrastive mixup). In this approach, the SSL model is adapted through additional pre-training using mixed data views created by interpolating samples from the source and the target domains. Our proposed adaptation method consistently outperforms the baseline system, using approximately 11 hours of adaptation data and requiring only 1 hour of adaptation time on a single GPU with WavLM-Large.
Authors
(none)
Tags
Stats
Related papers
- Automatic Data Augmentation For Domain Adapted Fine-tuning Of Self-supervised Speech Representations (2023)0.00
- Boosting Cross-domain Speech Recognition With Self-supervision (2022)0.00
- How To Learn A New Language? An Efficient Solution For Self-supervised Learning Models Unseen Languages Adaption In Low-resource Scenario (2024)0.00
- Deploying Self-supervised Learning In The Wild For Hybrid Automatic Speech Recognition (2022)0.00
- Multi-variant Consistency Based Self-supervised Learning For Robust Automatic Speech Recognition (2021)0.00
- Combining Spectral And Self-supervised Features For Low Resource Speech Recognition And Translation (2022)8.82
- Weakly-supervised Speech Pre-training: A Case Study On Target Speech Recognition (2023)8.09
- Unsupervised Multi-channel Separation And Adaptation (2023)4.52