仅用需删除数据即可实现语音情感识别模型的遗忘，保护隐私且无需额外数据。
Machine Unlearning in Speech Emotion Recognition via Forget Set Alone
- 基于对抗攻击思想，仅用待删数据微调预训练模型。
- 成功移除目标数据知识，测试集准确率仍保持高位。
- 适合隐私敏感场景，降低对额外数据和算力的需求。
语音情感识别旨在从语音信号中识别情绪状态，广泛应用于人机交互、教育、医疗等领域。由于语音数据包含大量敏感信息，用户可能因隐私担忧要求删除部分数据。现有机器遗忘方法大多依赖于被遗忘样本之外的数据，但在数据无法共享且大数据环境下，这会带来计算资源开销大、部署困难等问题。本文提出一种基于对抗攻击的新方法，仅使用待遗忘的数据对预训练语音情感识别模型进行微调。实验结果表明，该方法能有效消除模型中与待遗忘数据相关的知识，同时在测试集上保持较高的情感识别性能。
原文摘要 · Abstract (English)
Speech emotion recognition aims to identify emotional states from speech signals and has been widely applied in human-computer interaction, education, healthcare, and many other fields. However, since speech data contain rich sensitive information, partial data can be required to be deleted by speakers due to privacy concerns. Current machine unlearning approaches largely depend on data beyond the samples to be forgotten. However, this reliance poses challenges when data redistribution is restricted and demands substantial computational resources in the context of big data. We propose a novel adversarial-attack-based approach that fine-tunes a pre-trained speech emotion recognition model using only the data to be forgotten. The experimental results demonstrate that the proposed approach can effectively remove the knowledge of the data to be forgotten from the model, while preserving high model performance on the test set for emotion recognition.
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。