Wake word (WW) spotting is challenging in far-field not only because of the interference in signal transmission but also the complexity in acoustic environments.
Since the WW model is trained with the AFE-processed audio data, its performance is sensitive to AFE variations, such as gain changes.
In this paper, we propose two new methods for detecting the endpoints of wake words in neural KWS that use single-stage word-level neural networks.
Finally, the max-pooling loss trained LSTM initialized with a cross-entropy pre-trained network shows the best performance, which yields $67. 6\%$ relative reduction compared to baseline feed-forward DNN in Area Under the Curve (AUC) measure.