用于多种语音处理任务的参数有效迁移学习
Parameter Efficient Transfer Learning for Various Speech Processing Tasks
摘要:
自监督模型的微调在包括语音处理在内的各种领域中是一种强大的迁移学习方法,因为它可以利用从大量未标记数据中获得的通用特征表示。然而,微调需要为每个下游任务设置新的参数,这是参数低效的。适配器架构被提出来部分解决这个问题,通过将轻量级的可学习模块插入到冻结的预训练模型中。然而,现有的适配器架构无法自适应地利用存储在不同层中的低到高级别的功能,这是解决各种语音处理任务所必需的。因此,我们提出了一个新的适配器架构,以获得各种语音任务的特征表示更灵活。在实验中,我们将此适配器WavLM四个语音任务。它的性能与朴素的微调相当或更好,只有11%的可学习参数。它还优于现有的适配器架构。
英文摘要:
Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data. Fine-tuning, however, requires a new parameter set for each downstream task, which is parameter inefficient. Adapter architecture is proposed to partially solve this issue by inserting lightweight learnable modules into a frozen pre-trained model. However, existing adapter architectures fail to adaptively leverage low- to high-level features stored in different layers, which is necessary for solving various kinds of speech processing tasks. Thus, we propose a new adapter architecture to acquire feature representations more flexibly for various speech tasks. In experiments, we applied this adapter to WavLM on four speech tasks. It performed on par or better than naive fine-tuning, with only 11% of learnable parameters. It also outperformed an existing adapter architecture.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。