arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.12657eess.AS
收藏

基于线性和非线性声学语义投影的Zero-Shot音频分类

Zero-Shot Audio Classification with Factored Linear and Nonlinear Acoustic-Semantic Projections

Huang Xie, Okko Räsänen, Tuomas Virtanen

摘要:

在本文中,我们研究了zero-shot学习音频分类,通过分解的线性和非线性的声学语义之间的投影音频实例和声音类。音频分类中的Zero-shot学习是指识别声音类别的音频实例的分类问题,这些音频实例没有可用的训练数据,而只有语义边信息。在本文中,我们通过采用分解的线性和非线性声学语义投影来解决零激发学习(zero-shot learning)。我们通过将秩分解应用于双线性模型来开发因子线性投影,并使用非线性激活函数(如tanh)来模拟声学嵌入和语义嵌入之间的非线性。实验结果表明,与传统的双线性模型相比,本文提出的投影方法能够有效地提高音频分类中zero-shot学习的分类性能。

英文摘要:

In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data but only semantic side information. In this paper, we address zero-shot learning by employing factored linear and nonlinear acoustic-semantic projections. We develop factored linear projections by applying rank decomposition to a bilinear model, and use nonlinear activation functions, such as tanh, to model the non-linearity between acoustic embeddings and semantic embeddings. Compared with the prior bilinear model, experimental results show that the proposed projection methods are effective for improving classification performance of zero-shot learning in audio classification.

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。

↑