mlsanityData to 14 Oct 2026

Deep Residual Learning for Small-Footprint Keyword Spotting

arXiv 1710.10361 ↗First posted 28 Oct 2017cs.CLcited by 68

Not on the map. Why?

Abstract (arXiv)

We explore the application of deep residual learning and dilated convolutions to the keyword spotting task, using the recently-released Google Speech Commands Dataset as our benchmark. Our best residual network (ResNet) implementation significantly outperforms Google's previous convolutional neural networks in terms of accuracy. By varying model depth and width, we can achieve compact models that also outperform previous small-footprint variants. To our knowledge, we are the first to examine these approaches for keyword spotting, and our results establish an open-source state-of-the-art reference to support the development of future speech-based interfaces.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 20; 2023: 9; 2024: 9; 2025: 7; 2026: 6.

68 papers.

Sort:

By area:

  1. 2021Broadcasted Residual Learning for Efficient Keyword Spottingcited by 48
  2. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  3. 2021Few-Shot Keyword Spotting in Any Languagecited by 27
  4. 2021Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Losscited by 25
  5. 2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
  6. 2022Asymmetric Temperature Scaling Makes Larger Networks Teach Well Againcited by 23
  7. 2021PQK: Model Compression via Pruning, Quantization, and Knowledge Distillationcited by 21
  8. 2021Differentiable Network Pruning for Microcontrollerscited by 16
  9. 2021Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networkscited by 15
  10. 2023Matching Latent Encoding for Audio-Text based Keyword Spottingcited by 15
  11. 2022XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaversecited by 14
  12. 2023The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any languagecited by 14
38 more
  1. 2021SubSpectral Normalization for Neural Audio Data Processingcited by 11
  2. 2023Flexible Keyword Spotting based on Homogeneous Audio-Text Embeddingcited by 10
  3. 2023Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statisticscited by 9
  4. 2022Progressive Continual Learning for Spoken Keyword Spottingcited by 8
  5. 2022Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spottingcited by 8
  6. 2022DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloadscited by 8
  7. 2023MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networkscited by 8
  8. 2022Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spottingcited by 7
  9. 2022Personalized Keyword Spotting through Multi-task Learningcited by 7
  10. 2021Ultra-Low Power Keyword Spotting at the Edgecited by 6
  11. 2024TeMPO: Efficient Time-Multiplexed Dynamic Photonic Tensor Core for Edge AI with Compact Slow-Light Electro-Optic Modulatorcited by 6
  12. 2023PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injectioncited by 5
  13. 2022Avoid Overfitting User Specific Information in Federated Keyword Spottingcited by 4
  14. 2022LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spottingcited by 4
  15. 2025AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spottingcited by 4
  16. 2021Text Anchor Based Metric Learning for Small-footprint Keyword Spottingcited by 3
  17. 2021EfficientWord-Net: An Open Source Hotword Detection Engine based on One-shot Learningcited by 3
  18. 2022Streaming Intended Query Detection using E2E Modeling for Continued Conversationcited by 3
  19. 2022HEiMDaL: Highly Efficient Method for Detection and Localization of wake-wordscited by 3
  20. 2022Filterbank Learning for Noise-Robust Small-Footprint Keyword Spottingcited by 3
  21. 2022Pex: Memory-efficient Microcontroller Deep Learning through Partial Executioncited by 3
  22. 2024Relational Proxy Loss for Audio-Text based Keyword Spottingcited by 3
  23. 2021Speech Enhancement for Wake-Up-Word detection in Voice Assistantscited by 2
  24. 2021Auto-KWS 2021 Challenge: Task, Datasets, and Baselinescited by 2
  25. 2021Encoder-Decoder Neural Architecture Optimization for Keyword Spottingcited by 2
  26. 2021Attention-Free Keyword Spottingcited by 2
  27. 2023To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinementcited by 2
  28. 2024Text-Aware Adapter for Few-Shot Keyword Spottingcited by 2
  29. 2021Prototype-based Personalized Pruningcited by 1
  30. 2022Learning Decoupling Features Through Orthogonality Regularizationcited by 1
  31. 2022Improving Voice Trigger Detection with Metric Learningcited by 1
  32. 2022Speech Augmentation Based Unsupervised Learning for Keyword Spottingcited by 1
  33. 2022I see what you hear: a vision-inspired method to localize wordscited by 1
  34. 2023Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensemblescited by 1
  35. 2024Sparse Binarization for Fast Keyword Spottingcited by 1
  36. 2024Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spottingcited by 1
  37. 2025Improving Pretrained YAMNet for Enhanced Speech Command Detection via Transfer Learningcited by 1
  38. 2025Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spottingcited by 1

50 most cited of 68 All 68 (JSON)