Litcius/Paper detail

Convmixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-Field Keyword Spotting

Dianwen Ng, Yunqi Chen, Biao Tian, Qiang Fu, Eng Siong Chng

2022ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)49 citationsDOI

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 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.

Topics & Concepts

Computer scienceKeyword spottingRobustness (evolution)Convolutional neural networkSpottingArtificial intelligenceSoftware deploymentSpeech recognitionDeep learningComputationMachine learningPattern recognition (psychology)AlgorithmChemistryBiochemistryGeneOperating systemSpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing
Convmixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-Field Keyword Spotting | Litcius