Attention-Free Keyword Spotting
This work addresses the keyword spotting problem for speech recognition applications, but it is incremental as it adapts existing MLP methods from vision to a new domain.
The paper tackled keyword spotting by exploring gated MLPs as an alternative to attention-based models, achieving competitive performance on Google Speech Commands V2-12 and V2-35 benchmarks with under 0.5 million parameters.
Till now, attention-based models have been used with great success in the keyword spotting problem domain. However, in light of recent advances in deep learning, the question arises whether self-attention is truly irreplaceable for recognizing speech keywords. We thus explore the usage of gated MLPs --previously shown to be alternatives to transformers in vision tasks-- for the keyword spotting task. We provide a family of highly efficient MLP-based models for keyword spotting, with less than 0.5 million parameters. We show that our approach achieves competitive performance on Google Speech Commands V2-12 and V2-35 benchmarks with much fewer parameters than self-attention-based methods.