In this paper, we propose a Boosting Tail Neural Network (BTNN) for improving the performance of Realtime Custom Keyword Spotting (RCKS) that is still an industrial challenge for demanding powerful classification ability with limited computation resources. Inspired by Brain Science that a brain is only partly activated for a nerve simulation and numerous machine learning algorithms are developed to use a batch of weak classifiers to resolve arduous problems, which are often proved to be effective. We show that this method is helpful to the RCKS problem. The proposed approach achieve better performances in terms of wakeup rate and false alarm. In our experiments compared with those traditional algorithms that use only one strong classifier, it gets 18\% relative improvement. We also point out that this approach may be promising in future ASR exploration.

翻译：本文提出了一种提升尾部神经网络（Boosting Tail Neural Network, BTNN），用于改进实时自定义关键词唤醒（Realtime Custom Keyword Spotting, RCKS）的性能。RCKS 在工业领域仍是一项挑战，要求在有限计算资源下具备强大的分类能力。受脑科学启发——大脑仅部分激活以响应神经刺激——众多机器学习算法通过利用一批弱分类器解决艰巨问题，并已被证明成效显著。我们表明，该方法对RCKS问题具有帮助。所提方法在唤醒率和误报率方面均取得了更优表现。在与仅使用单一强分类器的传统算法对比实验中，该方法获得了18%的相对提升。我们还指出，这一方法在未来自动语音识别（ASR）探索中具有潜力。