Privacy preserving speech analysis using emotion filtering at the edge
Privacy preserving speech analysis using emotion filtering at the edge
复制标题
使用边缘情感过滤进行隐私保护语音分析
DOI：
10.1145/3356250.3361947
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Aloufi R
中科院分区：
文献类型：
--
作者：
Aloufi R
语音控制设备和服务在消费者物联网中很常见。基于云的分析服务使用语音识别技术从语音输入中提取信息。服务提供商可以建立用户的人口统计、偏好和情绪状态等的详细资料，因此可能严重损害隐私。为了解决这个问题，提出了用户和云服务之间的隐私保护中间层，通过生成用于转发的中和信号来直接在边缘设备处净化语音输入。我们发现，基于CycleGAN并部署在Raspberry Pi上的训练模型能够识别和删除约91%的敏感情绪状态信息，并且对语音识别准确性的损失最小。
Voice controlled devices and services are commonplace in consumer IoT. Cloud-based analysis services extract information from voice input using speech recognition techniques. Services providers can build detailed profiles of users' demographics, preferences and emotional states, etc., and may therefore significantly compromise privacy. To address this problem, a privacy-preserving intermediate layer between users and cloud services is proposed to sanitize voice input directly at edge devices by generating neutralized signals for forwarding. We show that a trained model, based on CycleGAN and deployed on a Raspberry Pi, enables identification and removal of sensitive emotional state information by ~91%, with minimal losses to speech recognition accuracy.