arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.08722eess.AScs.LGcs.SDstat.ML
收藏

一种新的注意力和序列到序列自动编码器的融合,以从语音中预测睡意

A Novel Fusion of Attention and Sequence to Sequence Autoencoders to Predict Sleepiness From Speech

University of Augsburg(奥格斯堡大学);Imperial College London(帝国理工学院);BMW AG(宝马股份公司)

Shahin Amiriparian, Pawel Winokurow, Vincent Karas, Sandra Ottl, Maurice Gerczuk, Björn W. Schuller

摘要:

受人类视觉系统的注意力机制和机器翻译领域的最新发展的启发,我们介绍了我们的基于注意力和递归序列到序列自动编码器,用于从音频文件中进行完全无监督的表示学习。特别是,我们测试了我们的新方法对基于语音的困倦识别任务的有效性。我们评估从两个自动编码器学习的表示,然后进行早期融合,以确定它们之间可能的互补性。在我们的框架中,我们首先从原始音频文件中提取Mel频谱图。其次,我们训练这些频谱图,这被认为是时间相关的频率向量的经常性自编码器。然后,我们提取自动编码器的特定全连接层的激活,这些层代表相应音频实例的频谱图的学习特征。最后,我们训练支持向量回归机对这些表示,以获得预测。在数据的发展分区上,我们通过利用注意力和非注意力自动编码器以及两种自动编码器表示的融合,分别实现了斯皮尔曼与卡罗林斯卡嗜睡量表上目标的相关系数为.324,.283和.320。在相同的顺序,我们实现了.311,.359和.367斯皮尔曼的相关系数的测试数据,表明我们提出的融合策略的适用性。

英文摘要:

Motivated by the attention mechanism of the human visual system and recent developments in the field of machine translation, we introduce our attention-based and recurrent sequence to sequence autoencoders for fully unsupervised representation learning from audio files. In particular, we test the efficacy of our novel approach on the task of speech-based sleepiness recognition. We evaluate the learnt representations from both autoencoders, and then conduct an early fusion to ascertain possible complementarity between them. In our frameworks, we first extract Mel-spectrograms from raw audio files. Second, we train recurrent autoencoders on these spectrograms which are considered as time-dependent frequency vectors. Afterwards, we extract the activations of specific fully connected layers of the autoencoders which represent the learnt features of spectrograms for the corresponding audio instances. Finally, we train support vector regressors on these representations to obtain the predictions. On the development partition of the data, we achieve Spearman's correlation coefficients of .324, .283, and .320 with the targets on the Karolinska Sleepiness Scale by utilising attention and non-attention autoencoders, and the fusion of both autoencoders' representations, respectively. In the same order, we achieve .311, .359, and .367 Spearman's correlation coefficients on the test data, indicating the suitability of our proposed fusion strategy.

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。

↑