AI Research into Spoken Keyword Spotting. Collection of PyTorch implementations of Spoken Keyword Spotting presented in research papers. Model architectures will not always mirror the ones proposed in the papers, but I have chosen to focus on getting the core ideas covered instead of getting every layer configuration right.
首先,把数据集的data文件夹放到:<当前文件夹>/dataset/atc/data
一共有五个基线模型,包括了各自的论文地址
Temporal Convolution for Real-time Keyword Spotting on Mobile Devices [Paper] [Code]
Broadcasted Residual Learning for Efficient Keyword Spotting [Paper] [Code]
MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition [Paper] [Code]
ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting [Paper] [Code]
Keyword transformer: A self-attention model for keyword spotting [Paper] [Code]
bash e1.sh
bash e2.sh
bash e3.sh
bash e4.sh