End-to-end Keyword Spotting Using Neural Architecture Search And Quantization

Abstract

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) operating on raw audio waveforms. After a suitable KWS model is found with NAS, we conduct quantization of weights and activations to reduce the memory footprint. We conduct extensive experiments on the Google speech commands dataset. In particular, we compare our end-to-end approach to mel-frequency cepstral coefficient (MFCC) based systems. For quantization, we compare fixed bit-width quantization and trained bit-width quantization. Using NAS only, we were able to obtain a highly efficient model with an accuracy of 95.55% using 75.7k parameters and 13.6M operations. Using trained bit-width quantization, the same model achieves a test accuracy of 93.76% while using on average only 2.91 bits per activation and 2.51 bits per

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keypeter2021end

Related papers

• Autokws: Keyword Spotting With Differentiable Architecture Search (2020)9.92
• Neural Architecture Search For Keyword Spotting (2020)10.61
• A Monaural Speech Enhancement Method For Robust Small-footprint Keyword Spotting (2019)0.00
• End-to-end Streaming Keyword Spotting (2018)12.10
• DCCRN-KWS: An Audio Bias Based Model For Noise Robust Small-footprint Keyword Spotting (2023)5.24
• Small-footprint Open-vocabulary Keyword Spotting With Quantized LSTM Networks (2020)0.00
• Small-footprint Keyword Spotting With Graph Convolutional Network (2019)10.48
• A Separable Temporal Convolution Neural Network With Attention For Small-footprint Keyword Spotting (2021)0.00