ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting
arXiv:2201.05863 · doi:10.1109/ICASSP43922.2022.9747025
Abstract
Building efficient architecture in neural speech processing is paramount to success in keyword spotting deployment. However, it is very challenging for lightweight models to achieve noise robustness with concise neural operations. In a real-world application, the user environment is typically noisy and may also contain reverberations. We proposed a novel feature interactive convolutional model with merely 100K parameters to tackle this under the noisy far-field condition. The interactive unit is proposed in place of the attention module that promotes the flow of information with more efficient computations. Moreover, curriculum-based multi-condition training is adopted to attain better noise robustness. Our model achieves 98.2% top-1 accuracy on Google Speech Command V2-12 and is competitive against large transformer models under the designed noise condition.
arXiv commentsubmitted to ICASSP 2022
References in corpus (6)
- MLP-Mixer: An all-MLP Architecture for Vision
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- Hello Edge: Keyword Spotting on Microcontrollers
- Keyword Transformer: A Self-Attention Model for Keyword Spotting
- Building and Evaluation of a Real Room Impulse Response Dataset
- Streaming keyword spotting on mobile devices