论文标题
通过对比嵌入重播对发言人的同意管理的动态认可
Dynamic Recognition of Speakers for Consent Management by Contrastive Embedding Replay
论文作者
论文摘要
需要语音助手听到对话和同意管理机制。可以使用说话者识别来实施同意管理。不给予同意的用户注册了他们的声音，并丢弃了所有进一步的录音。必须有效地处理基于动态的注册，删除和重新注册的动态注册，删除和重新注册，因此基于建筑发言人的同意管理必须有效地进行挑战。这项工作提出了解决上述挑战的同意管理系统。采用基于对比的培训来学习潜在的扬声器归纳偏见。扬声器桶的对比功能经过了几步，并充当重播缓冲区。这些特征是使用多控制的随机采样器进行分类逐渐选择的。此外，提出了使用一部分旧话语，删除和重新注册说话者进行动态注册的新方法。结果验证了所提出方法的记忆效率和动态功能，并优于文献中现有方法。
Voice assistants overhear conversations and a consent management mechanism is required. Consent management can be implemented using speaker recognition. Users that do not give consent enrol their voice and all their further recordings are discarded. Building speaker recognition-based consent management is challenging as dynamic registration, removal, and re-registration of speakers must be efficiently handled. This work proposes a consent management system addressing the aforementioned challenges. A contrastive based training is applied to learn the underlying speaker equivariance inductive bias. The contrastive features for buckets of speakers are trained a few steps into each iteration and act as replay buffers. These features are progressively selected using a multi-strided random sampler for classification. Moreover, new methods for dynamic registration using a portion of old utterances, removal, and re-registration of speakers are proposed. The results verify memory efficiency and dynamic capabilities of the proposed methods and outperform the existing approach from the literature.
