Multi-accent Speech Separation with One Shot Learning
arXiv:2106.11713
Abstract
Speech separation is a problem in the field of speech processing that has been studied in full swing recently. However, there has not been much work studying a multi-accent speech separation scenario. Unseen speakers with new accents and noise aroused the domain mismatch problem which cannot be easily solved by conventional joint training methods. Thus, we applied MAML and FOMAML to tackle this problem and obtained higher average Si-SNRi values than joint training on almost all the unseen accents. This proved that these two methods do have the ability to generate well-trained parameters for adapting to speech mixtures of new speakers and accents. Furthermore, we found out that FOMAML obtains similar performance compared to MAML while saving a lot of time.
arXiv commentAccepted at ACL 2021 Meta Learning for NLP
References in corpus (10)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Matching Networks for One Shot Learning
- Meta-Learning with Latent Embedding Optimization
- Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning
- Meta-Learning for Low-Resource Neural Machine Translation
- DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
- One Shot Learning for Speech Separation
- Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
- Improved Meta-Learning Training for Speaker Verification