Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies
Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies
复制标题
用于从局部依赖性学习语音表示的非自回归预测编码
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
James R. Glass
中科院分区：
文献类型：
--
作者：
Alexander H. Liu;Yu;James R. Glass
自监督语音表示已被证明在各种语音应用中是有效的。然而，现有的表示学习方法在生成表示时通常依赖于自回归模型和/或观察到的全局依赖关系。在这项工作中，我们提出了非自回归预测编码(NPC)，这是一种自我监督的方法，通过只依赖于语音的局部依赖来以非自回归的方式学习语音表示。NPC在概念上有一个简单的目标，并且可以通过引入的掩码卷积块来容易地实现。由于NPC在时间上是可并行化的，并且无论输入序列的长度如何，对于每个时间步长都有固定的推理时间，因此NPC提供了显著的加速比。通过与其他方法的理论和实证比较，讨论并验证了NPC方法的有效性。实验结果表明，在语音分类和说话人分类实验中，NPC表示与其他方法相当，但效率更高。
Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies while generating the representation. In this work, we propose Non-Autoregressive Predictive Coding (NPC), a self-supervised method, to learn a speech representation in a non-autoregressive manner by relying only on local dependencies of speech. NPC has a conceptually simple objective and can be implemented easily with the introduced Masked Convolution Blocks. NPC offers a significant speedup for inference since it is parallelizable in time and has a fixed inference time for each time step regardless of the input sequence length. We discuss and verify the effectiveness of NPC by theoretically and empirically comparing it with other methods. We show that the NPC representation is comparable to other methods in speech experiments on phonetic and speaker classification while being more efficient.