arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.04488cs.CLcs.SDeess.AS
收藏

基于流式Transformers的唤醒字检测

Wake Word Detection with Streaming Transformers

AppTek(AppTek公司)

Yiming Wang, Hang Lv, Daniel Povey, Lei Xie, Sanjeev Khudanpur

摘要:

现代尾波检测系统通常依赖于神经网络进行声学建模。Transformers最近在各种序列建模任务中表现出优于LSTM和卷积网络的性能,具有更好的时间建模能力。然而,目前尚不清楚这种优势是否仍然适用于短距离时间建模,如唤醒词检测。此外,由于其非流性质和二次时间和空间复杂度,vanilla Transformer不能直接应用于任务。在本文中,我们探讨了几种变体的块明智的流Transformers专门用于唤醒词检测在最近提出的LF-MMI系统,包括前瞻性到下一个块,梯度停止,不同的位置嵌入方法和块之间添加同层依赖的性能。我们在Mobvoi唤醒词数据集上的实验表明,我们提出的Transformer模型在具有可比模型大小的相同误报率下,在误报率方面平均优于基线卷积网络25%,同时仍然保持线性复杂度w.r.t.序列长度。

英文摘要:

Modern wake word detection systems usually rely on neural networks for acoustic modeling. Transformers has recently shown superior performance over LSTM and convolutional networks in various sequence modeling tasks with their better temporal modeling power. However it is not clear whether this advantage still holds for short-range temporal modeling like wake word detection. Besides, the vanilla Transformer is not directly applicable to the task due to its non-streaming nature and the quadratic time and space complexity. In this paper we explore the performance of several variants of chunk-wise streaming Transformers tailored for wake word detection in a recently proposed LF-MMI system, including looking-ahead to the next chunk, gradient stopping, different positional embedding methods and adding same-layer dependency between chunks. Our experiments on the Mobvoi wake word dataset demonstrate that our proposed Transformer model outperforms the baseline convolution network by 25% on average in false rejection rate at the same false alarm rate with a comparable model size, while still maintaining linear complexity w.r.t. the sequence length.

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。

↑