# MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition

arXiv: https://arxiv.org/abs/2004.08531 · HTML: https://mlsanity.com/paper/2004.08531/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2020.

## Built on by (most cited first, 30 of 36)

- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Keyword Transformer: A Self-Attention Model for Keyword Spotting](https://mlsanity.com/paper/2104.00769/) (2021)
- [Broadcasted Residual Learning for Efficient Keyword Spotting](https://mlsanity.com/paper/2106.04140/) (2021)
- [Out-of-Distribution Representation Learning for Time Series Classification](https://mlsanity.com/paper/2209.07027/) (2022)
- [Learning Efficient Representations for Keyword Spotting with Triplet Loss](https://mlsanity.com/paper/2101.04792/) (2021)
- [DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2308.02282/) (2023)
- [SepTr: Separable Transformer for Audio Spectrogram Processing](https://mlsanity.com/paper/2203.09581/) (2022)
- [Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction](https://mlsanity.com/paper/2306.09313/) (2023)
- [Teaching keyword spotters to spot new keywords with limited examples](https://mlsanity.com/paper/2106.02443/) (2021)
- [Open-vocabulary Keyword-spotting with Adaptive Instance Normalization](https://mlsanity.com/paper/2309.08561/) (2023)
- [When the Inference Meets the Explicitness or Why Multimodality Can Make Us Forget About the Perfect Predictor](https://mlsanity.com/paper/2602.18850/) (2026)
- [Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition](https://mlsanity.com/paper/2110.03894/) (2021)
- [Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset](https://mlsanity.com/paper/2510.21038/) (2025)
- [Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices](https://mlsanity.com/paper/2103.17142/) (2021)
- [Encoder-Decoder Neural Architecture Optimization for Keyword Spotting](https://mlsanity.com/paper/2106.02738/) (2021)
- [Attention-Free Keyword Spotting](https://mlsanity.com/paper/2110.07749/) (2021)
- [Implicit Acoustic Echo Cancellation for Keyword Spotting and Device-Directed Speech Detection](https://mlsanity.com/paper/2111.10639/) (2021)
- [ImportantAug: a data augmentation agent for speech](https://mlsanity.com/paper/2112.07156/) (2021)
- [Cascaded Cross-Modal Transformer for Audio-Textual Classification](https://mlsanity.com/paper/2401.07575/) (2024)
- [Improving Voice Trigger Detection with Metric Learning](https://mlsanity.com/paper/2204.02455/) (2022)
- [Speech Augmentation Based Unsupervised Learning for Keyword Spotting](https://mlsanity.com/paper/2205.14329/) (2022)
- [Sparse Binarization for Fast Keyword Spotting](https://mlsanity.com/paper/2406.06634/) (2024)
- [Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point](https://mlsanity.com/paper/2407.02610/) (2024)
- [TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild](https://mlsanity.com/paper/2603.21478/) (2026)
- [Cross Entropy in Deep Learning of Classifiers Is Unnecessary -- ISBE Error is All You Need](https://mlsanity.com/paper/2311.16357/) (2023)
- [Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition](https://mlsanity.com/paper/2406.02488/) (2024)
- [RepCNN: Micro-sized, Mighty Models for Wakeword Detection](https://mlsanity.com/paper/2406.02652/) (2024)
- [Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learning](https://mlsanity.com/paper/2406.18313/) (2024)
- [Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology](https://mlsanity.com/paper/2409.00356/) (2024)
- [Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space](https://mlsanity.com/paper/2409.12745/) (2024)

## Abstract (arXiv)

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.