arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.12908eess.AScs.SD
收藏

带语音调制丢失的自监督学习

Self-supervised Learning with Speech Modulation Dropout

Johns Hopkins University(约翰斯·霍普金斯大学)

Samik Sadhu, Hynek Hermansky

摘要:

我们证明,训练一个基于多头自我注意力的深度网络来预测1.5秒内被删除的、信息密集的2-8 Hz语音调制,是一种有效的方法,可以让机器学习使用时域上下文信息来提取语音调制。我们的工作表明,一旦在大量未标记的数据上进行训练,自我注意层的输出会随着时间的推移而变化,调制峰值为4 Hz。这些预训练的层可用于初始化自动语音识别系统的部分,以大大减少其对标记语音数据的依赖。

英文摘要:

We show that training a multi-headed self-attention-based deep network to predict deleted, information-dense 2-8 Hz speech modulations over a 1.5-second section of a speech utterance is an effective way to make machines learn to extract speech modulations using time-domain contextual information. Our work exhibits that, once trained on large volumes of unlabelled data, the outputs of the self-attention layers vary in time with a modulation peak at 4 Hz. These pre-trained layers can be used to initialize parts of an Automatic Speech Recognition system to reduce its reliance on labeled speech data greatly.

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。

↑