用对比学习训练的Transformer模型，让极低资源语言也能精准听懂关键词。
Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings
- 用对比学习直接优化声学词嵌入空间，无需复杂预训练
- 在卢干达语和巴马拉语上均超越现有方法，提升显著
- 特别适合数据极少的语言，如非洲本土方言
我们提出一种新方法——对比Transformer，用于极低资源条件下的关键词检测。该模型为仅含编码器的架构，通过归一化温度缩放交叉熵损失（NT-Xent）直接优化嵌入空间。我们在卢干达语和巴马拉语（后者是严重资源匮乏的语言）的广播音频上进行关键词检测实验。与多种现有声学词嵌入方法相比，包括基于大模型自监督预训练的方法、先前使用NT-Xent损失的循环编码器，以及动态时间规整（DTW）基线，所提方法在两种语言中均表现出更优性能，证明其在极低资源场景下具有显著优势。
原文摘要 · Abstract (English)
We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWEs) for the purpose of very low-resource keyword spotting. The ContrastiveTransformer, an encoder-only model, directly optimises the embedding space using normalised temperature-scaled cross entropy (NT-Xent) loss. We use this model to perform keyword spotting for radio broadcasts in Luganda and Bambara, the latter a severely under-resourced language. We compare our model to various existing AWE approaches, including those constructed from large pre-trained self-supervised models, a recurrent encoder which previously used the NT-Xent loss, and a DTW baseline. We demonstrate that the proposed contrastive transformer approach offers performance improvements over all considered existing approaches to very low-resource keyword spotting in both languages.
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。