MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition
Preprint
Abstract
We present an MatchboxNet - an end-to-end neural network for speech command recognition. MatchboxNet is a deep residual network composed from blocks of 1D time-channel separable convolution, batch-normalization, ReLU and dropout layers. MatchboxNet reaches state-of-the-art accuracy on the Google Speech Commands dataset while having significantly fewer parameters than similar models. The small footprint of MatchboxNet makes it an attractive candidate for devices with limited computational resources. The model is highly scalable, so model accuracy can be improved with modest additional memory and compute. Finally, we show how intensive data augmentation using an auxiliary noise dataset improves robustness in the presence of background noise.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- On Feature Normalization and Data Augmentation2021
- Bag of Tricks for Image Classification with Convolutional Neural Networks2019
- Streaming End-to-end Speech Recognition for Mobile Devices2019
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Deep Residual Learning for Image Recognition2016
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Tandem connectionist feature extraction for conventional HMM systems2002
- IPA: improved phone modelling with recurrent neural networks1994
- Global optimization of a neural network-hidden Markov model hybridIEEE Transactions on Neural Networks, 1992
- A time-delay neural network architecture for isolated word recognitionNeural Networks, 1990