# On training targets for noise-robust voice activity detection

arXiv: https://arxiv.org/abs/2102.07445 · HTML: https://mlsanity.com/paper/2102.07445/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2021.

## Built on by (most cited first, 6 of 6)

- [Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems](https://mlsanity.com/paper/2211.00786/) (2022)
- [In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms](https://mlsanity.com/paper/2309.02393/) (2023)
- [SECP: A Speech Enhancement-Based Curation Pipeline For Scalable Acquisition Of Clean Speech](https://mlsanity.com/paper/2402.12482/) (2024)
- [Tiny Noise-Robust Voice Activity Detector for Voice Assistants](https://mlsanity.com/paper/2507.22157/) (2025)
- [Real-time Speech Interruption Analysis: From Cloud to Client Deployment](https://mlsanity.com/paper/2210.13334/) (2022)
- [Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation](https://mlsanity.com/paper/2211.02944/) (2022)

## Abstract (arXiv)

The task of voice activity detection (VAD) is an often required module in various speech processing, analysis and classification tasks. While state-of-the-art neural network based VADs can achieve great results, they often exceed computational budgets and real-time operating requirements. In this work, we propose a computationally efficient real-time VAD network that achieves state-of-the-art results on several public real recording datasets. We investigate different training targets for the VAD and show that using the segmental voice-to-noise ratio (VNR) is a better and more noise-robust training target than the clean speech level based VAD. We also show that multi-target training improves the performance further.