论文标题
使用双向晶格复发的神经网络从LVCSR假设晶格中检测语音触发器检测
Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks
论文作者
论文摘要
我们提出了一种方法，以通过神经网络后处理服务器端大型播音员连续语音识别器（LVCSR）的假设晶格来减少启用语音的个人助手的虚假语音触发器。我们首先讨论如何使用已知技术从假设晶格中获得触发短语的后验概率的估计值，然后研究以更明确的数据驱动，歧视性的方式来处理晶格的统计模型。我们建议使用双向晶格复发神经网络（Latticernn）进行任务，并证明它可以显着提高使用使用1好的结果或后部的检测准确性。
We propose a method to reduce false voice triggers of a speech-enabled personal assistant by post-processing the hypothesis lattice of a server-side large-vocabulary continuous speech recognizer (LVCSR) via a neural network. We first discuss how an estimate of the posterior probability of the trigger phrase can be obtained from the hypothesis lattice using known techniques to perform detection, then investigate a statistical model that processes the lattice in a more explicitly data-driven, discriminative manner. We propose using a Bidirectional Lattice Recurrent Neural Network (LatticeRNN) for the task, and show that it can significantly improve detection accuracy over using the 1-best result or the posterior.
