mlsanityData to 7 Oct 2026

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

arXiv 2004.08531 ↗First posted 18 Apr 2020eess.AScited by 36

Not on the map. Why?

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.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 4; 2023: 4; 2024: 8; 2025: 2; 2026: 7.

36 papers.

Sort:

By area:

  1. 2021AST: Audio Spectrogram Transformercited by 634
  2. 2021Keyword Transformer: A Self-Attention Model for Keyword Spottingcited by 59
  3. 2021Broadcasted Residual Learning for Efficient Keyword Spottingcited by 47
  4. 2022Out-of-Distribution Representation Learning for Time Series Classificationcited by 30
  5. 2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
  6. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  7. 2022SepTr: Separable Transformer for Audio Spectrogram Processingcited by 15
  8. 2023Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correctioncited by 14
  9. 2021Teaching keyword spotters to spot new keywords with limited examplescited by 9
  10. 2023Open-vocabulary Keyword-spotting with Adaptive Instance Normalizationcited by 8
  11. 2026When the Inference Meets the Explicitness or Why Multimodality Can Make Us Forget About the Perfect Predictorcited by 4
  12. 2021Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognitioncited by 3
24 more
  1. 2025Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Datasetcited by 3
  2. 2021Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matricescited by 2
  3. 2021Encoder-Decoder Neural Architecture Optimization for Keyword Spottingcited by 2
  4. 2021Attention-Free Keyword Spottingcited by 2
  5. 2021Implicit Acoustic Echo Cancellation for Keyword Spotting and Device-Directed Speech Detectioncited by 2
  6. 2021ImportantAug: a data augmentation agent for speechcited by 2
  7. 2024Cascaded Cross-Modal Transformer for Audio-Textual Classificationcited by 2
  8. 2022Improving Voice Trigger Detection with Metric Learningcited by 1
  9. 2022Speech Augmentation Based Unsupervised Learning for Keyword Spottingcited by 1
  10. 2024Sparse Binarization for Fast Keyword Spottingcited by 1
  11. 2024Towards Federated Learning with On-device Training and Communication in 8-bit Floating Pointcited by 1
  12. 2026TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wildcited by 1
  13. 2023Cross Entropy in Deep Learning of Classifiers Is Unnecessary -- ISBE Error is All You Needcited by 0
  14. 2024Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognitioncited by 0
  15. 2024RepCNN: Micro-sized, Mighty Models for Wakeword Detectioncited by 0
  16. 2024Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learningcited by 0
  17. 2024Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technologycited by 0
  18. 2024Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Spacecited by 0
  19. 2025Keyword Mamba: Spoken Keyword Spotting with State Space Modelscited by 0
  20. 2026EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spottingcited by 0
  21. 2026PCOV-KWS: Multi-task Learning for Personalized Customizable Open Vocabulary Keyword Spottingcited by 0
  22. 2026Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifiercited by 0
  23. 2026Evaluating the Effectiveness of SechKAN on 1D Datacited by 0
  24. 2026Sub-Model Short-Term Memory Convolutions for Keyword Spotting Systems on Devicecited by 0