注意力模型的正则化前向-后向解码器
Regularized Forward-Backward Decoder for Attention Models
摘要:
注意力模型是语音识别研究的热点之一。到目前为止,许多研究主要集中在编码器结构或注意力模块,以提高这些模型的性能。然而,大多数人忽略了解码器。在本文中,我们提出了一种新的正则化技术,将第二个解码器在训练阶段。该解码器预先在时间反转的目标标签上进行了优化,并通过添加来自未来上下文的知识来支持训练期间的标准解码器。由于它只在训练过程中添加,因此我们不会改变网络的基本结构或在解码过程中增加复杂性。我们在较小的TEDLIUMv 2和较大的LibriSpeech数据集上评估了我们的方法,并在两者上实现了一致的改进。
英文摘要:
Nowadays, attention models are one of the popular candidates for speech recognition. So far, many studies mainly focus on the encoder structure or the attention module to enhance the performance of these models. However, mostly ignore the decoder. In this paper, we propose a novel regularization technique incorporating a second decoder during the training phase. This decoder is optimized on time-reversed target labels beforehand and supports the standard decoder during training by adding knowledge from future context. Since it is only added during training, we are not changing the basic structure of the network or adding complexity during decoding. We evaluate our approach on the smaller TEDLIUMv2 and the larger LibriSpeech dataset, achieving consistent improvements on both of them.
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。