Spot keywords from very noisy and mixed speech
Not on the map. Why?
Abstract (arXiv)
Most existing keyword spotting research focuses on conditions with slight or moderate noise. In this paper, we try to tackle a more challenging task: detecting keywords buried under strong interfering speech (10 times higher than the keyword in amplitude), and even worse, mixed with other keywords. We propose a novel Mix Training (MT) strategy that encourages the model to discover low-energy keywords from noisy and mixed speech. Experiments were conducted with a vanilla CNN and two EfficientNet (B0/B2) architectures. The results evaluated with the Google Speech Command dataset demonstrated that the proposed mix training approach is highly effective and outperforms standard data augmentation and mixup training.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 36 references that are in the map. First posted on arXiv 28 May 2023.
Builds on
20 of 36 references.
References · 20
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
- 2020How Does Mixup Help With Robustness and Generalization?cited by 193
- 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
- 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 127
- 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
- 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
- 2016Trainable Frontend For Robust and Far-Field Keyword Spottingcited by 32
- 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
- 2017End-to-End ASR-free Keyword Search from Speechcited by 19
8 more
- 2017Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Modelscited by 19
- 2020Towards Data-efficient Modeling for Wake Word Spottingcited by 13
- 2021Noisy student-teacher training for robust keyword spottingcited by 10
- 2018Data Augmentation for Robust Keyword Spotting under Playback Interferencecited by 8
- 2021Feature learning for efficient ASR-free keyword spotting in low-resource languagescited by 6
- 2022MixupE: Understanding and Improving Mixup from Directional Derivative Perspectivecited by 6
- 2021Speech Enhancement for Wake-Up-Word detection in Voice Assistantscited by 2
- 2022Speech Augmentation Based Unsupervised Learning for Keyword Spottingcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.