Paper ID | SPE-41.5 | ||
Paper Title | MARBLENET: DEEP 1D TIME-CHANNEL SEPARABLE CONVOLUTIONAL NEURAL NETWORK FOR VOICE ACTIVITY DETECTION | ||
Authors | Fei Jia, Somshubra Majumdar, Boris Ginsburg, NVIDIA Corporation, United States | ||
Session | SPE-41: Voice Activity and Disfluency Detection | ||
Location | Gather.Town | ||
Session Time: | Thursday, 10 June, 15:30 - 16:15 | ||
Presentation Time: | Thursday, 10 June, 15:30 - 16:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-VAD] Voice Activity Detection and End-pointing | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | 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. |