用自监督模型提升少样本语音关键词识别准确率
Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models
- 用Wav2Vec 2.0+子中心ArcFace提取强区分性特征
- 10样本下在GSC数据集上准确率从33.4%提至74.1%
- 轻量ResNet+注意力降维，适合边缘设备部署
关键词检测对电池供电的边缘设备实现免触交互至关重要。少样本关键词检测（FS-KWS）通过仅需少量示例即可识别自定义关键词，解决了传统系统在可扩展性和适应性上的难题。然而，现有方法在资源受限的边缘环境中仍存在准确率不足的问题。为此，本文提出一种训练方案，利用自监督学习模型进行鲁棒特征提取、维度压缩与知识蒸馏。教师模型基于Wav2Vec 2.0，采用子中心ArcFace损失，增强类间可分性与类内紧凑性。为实现边缘部署，引入基于注意力的维度压缩，并训练标准轻量级ResNet15学生模型。在多语言口语词汇语料库（MSWC）英文部分及Google语音命令（GSC）数据集上评估。显著地，在GSC数据集上10样本条件下，于1%误报率下分类准确率从33.4%提升至74.1%，大幅改善实际应用可行性。
原文摘要 · Abstract (English)
Keyword Spotting plays a critical role in enabling hands-free interaction for battery-powered edge devices. Few-Shot Keyword Spotting (FS-KWS) addresses the scalability and adaptability challenges of traditional systems by enabling recognition of custom keywords with only a few examples. However, existing FS-KWS systems achieve subpar accuracy at desirable false acceptance rates, particularly in resource-constrained edge environments. To address these issues, we propose a training scheme that leverages self-supervised learning models for robust feature extraction, dimensionality reduction, and knowledge distillation. The teacher model, based on Wav2Vec 2.0 is trained using Sub-center ArcFace loss, which enhances inter-class separability and intra-class compactness. To enable efficient deployment on edge devices, we introduce attention-based dimensionality reduction and train a standard lightweight ResNet15 student model. We evaluate the proposed approach on the English portion of the Multilingual Spoken Words Corpus (MSWC) and the Google Speech Commands (GSC) datasets. Notably, the proposed training method improves the 10-shot classification accuracy from 33.4% to 74.1% on 11 classes at 1% false alarm accuracy on the GSC dataset, thus making it significantly better-suited for a real use case scenario.
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。