用生成式元持续学习实现千类语音词的少样本分类
Scaling few-shot spoken word classification with generative meta-continual learning
- 提出GeMCL算法，支持连续学习上千类语音词
- 仅5次样本/类，训练时间不到基线1/100
- 适合需要快速适应新语音类别的实际场景
少样本语音词分类通常局限于少量类别，而本文探索了大规模少样本语音词分类的潜力：在每类仅5个样本的情况下，让模型学会区分1000个类别。通过使用生成式元持续学习（GeMCL）算法进行训练，并与反复微调或冻结的基线方法对比，结果表明，GeMCL展现出极强的稳定性。尽管其性能未始终超越反复全微调的HuBERT模型或冻结的HuBERT+反复训练分类头，但其性能可媲美后者，同时训练速度提升2000倍，数据使用量不足一半，训练时间减少两个数量级。
原文摘要 · Abstract (English)
Few-shot spoken word classification has largely been developed for applications where a small number of classes is considered, and so the potential of larger-scale few-shot spoken word classification remains untapped. This paper investigates the potential of a spoken word classifier to sequentially learn to distinguish between 1000 classes when it is given only five shots per class. We demonstrate that this scaling capability exists by training a model using the Generative Meta-Continual Learning (GeMCL) algorithm and comparing it to repeatedly trained or finetuned baselines. We find that GeMCL produces exceptionally stable performance, and although it does not always outperform a repeatedly fully-finetuned HuBERT model nor a frozen HuBERT model with a repeatedly trained classifier head, it produces comparable performance to the latter while adapting 2000 times faster, having been trained less than half of the data for two orders of magnitude less time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。