Personal VAD: Speaker-conditioned Voice Activity Detection

Abstract

In this paper, we propose "personal VAD", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming on-device speech recognition system, such that it only triggers for the target user, which helps reduce the computational cost and battery consumption, especially in scenarios where a keyword detector is unpreferable. We achieve this by training a VAD-alike neural network that is conditioned on the target speaker embedding or the speaker verification score. For each frame, personal VAD outputs the probabilities for three classes: non-speech, target speaker speech, and non-target speaker speech. Under our optimal setup, we are able to train a model with only 130K parameters that outperforms a baseline system where individually trained standard VAD and speaker recognition networks are combined to perform the same task.

Stats

• citations54
• S2 citations—
• github stars0
• HF likes0
• heat score13.05
• arxiv keyding2019personal

Related papers

• Hywa: Hypernetwork Weight Adapting Personalized Voice Activity Detection (2025)0.00
• Self-adaptive Soft Voice Activity Detection Using Deep Neural Networks For Robust Speaker Verification (2019)6.77
• Comparative Analysis Of Personalized Voice Activity Detection Systems: Assessing Real-world Effectiveness (2024)0.00
• Self-supervised Pretraining For Robust Personalized Voice Activity Detection In Adverse Conditions (2023)6.34
• Semantic VAD: Low-latency Voice Activity Detection For Speech Interaction (2023)6.34
• Noise-robust Target-speaker Voice Activity Detection Through Self-supervised Pretraining (2025)0.00
• Advancing VAD Systems Based On Multi-task Learning With Improved Model Structures (2023)0.00
• Voice Activity Detection: Merging Source And Filter-based Information (2019)13.50