# MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection

arXiv: https://arxiv.org/abs/2010.13886 · HTML: https://mlsanity.com/paper/2010.13886/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks](https://mlsanity.com/paper/2303.00733/) (2023)
- [Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition](https://mlsanity.com/paper/2108.04228/) (2021)
- [SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks](https://mlsanity.com/paper/2408.13040/) (2024)
- [UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions](https://mlsanity.com/paper/2310.02973/) (2023)
- [The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments](https://mlsanity.com/paper/2406.09494/) (2024)
- [Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environments](https://mlsanity.com/paper/2311.12564/) (2023)
- [CASPER: A Large Scale Spontaneous Speech Dataset](https://mlsanity.com/paper/2506.00267/) (2025)
- [Efficient Multimodal Neural Networks for Trigger-less Voice Assistants](https://mlsanity.com/paper/2305.12063/) (2023)
- [acoupi: An Open-Source Python Framework for Deploying Bioacoustic AI Models on Edge Devices](https://mlsanity.com/paper/2501.17841/) (2025)
- [Tiny Noise-Robust Voice Activity Detector for Voice Assistants](https://mlsanity.com/paper/2507.22157/) (2025)
- [HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants](https://mlsanity.com/paper/2510.12947/) (2025)
- [VAD to the Bone: Ultra-Tiny Speech Activity Detection for Edge Deployment](https://mlsanity.com/paper/2607.25870/) (2026)

## Abstract (arXiv)

We present MarbleNet, an end-to-end neural network for Voice Activity Detection (VAD). MarbleNet is a deep residual network composed from blocks of 1D time-channel separable convolution, batch-normalization, ReLU and dropout layers. When compared to a state-of-the-art VAD model, MarbleNet is able to achieve similar performance with roughly 1/10-th the parameter cost. We further conduct extensive ablation studies on different training methods and choices of parameters in order to study the robustness of MarbleNet in real-world VAD tasks.