用于设备引导的话语检测的具有因果均值聚合的流传输ResLSTM
Streaming ResLSTM with Causal Mean Aggregation for Device-Directed Utterance Detection
摘要：
在本文中，我们提出了一个流模型来区分语音查询的智能家居设备从背景语音。所提出的模型由具有剩余连接的多个CNN层组成，然后是堆叠的LSTM架构。通过使用单向LSTM层和因果平均聚合层来形成直到当前帧的最终话语级预测，从而实现流传输能力。为了避免在线流式推理过程中的冗余计算，我们为每个卷积操作使用缓存机制。在设备导向与非设备导向任务上的实验结果表明，与我们以前在这个任务上的最佳模型相比，该模型产生了41%的相等错误率降低。此外，我们表明，该模型是能够准确地预测较早的时间相比，基于注意力的模型。
英文摘要：
In this paper, we propose a streaming model to distinguish voice queries intended for a smart-home device from background speech. The proposed model consists of multiple CNN layers with residual connections, followed by a stacked LSTM architecture. The streaming capability is achieved by using unidirectional LSTM layers and a causal mean aggregation layer to form the final utterance-level prediction up to the current frame. In order to avoid redundant computation during online streaming inference, we use a caching mechanism for every convolution operation. Experimental results on a device-directed vs. non device-directed task show that the proposed model yields an equal error rate reduction of 41% compared to our previous best model on this task. Furthermore, we show that the proposed model is able to accurately predict earlier in time compared to the attention-based models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
