Abstract
In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models. Latent variables indeed encode both transferable distributional information and structural relationships. Thus the distributions of the source latent variables (prior) can be combined with the knowledge learned from the target data (likelihood) to yield the distributions of the target latent variables (posterior) with the goal of addressing acoustic mismatches between training and testing conditions. The prior knowledge transfer is accomplished through Variational Bayes (VB). In addition, we also investigate Maximum a Posteriori (MAP) based Bayesian adaptation. Experimental results on device adaptation in acoustic scene classification show that our proposed approaches can obtain good improvements on target devices, and consistently outperforms other cut-edging algorithms.
Abstract (translated)
在这项工作中,我们旨在通过专注于在深度神经网络(DNN)模型中估计潜在变量来建立一个贝叶斯自适应学习框架。事实上,潜在变量确实编码了可转移的分布信息和结构关系。因此,源潜在变量的分布(先验)可以与目标数据(后验)知识相结合,以产生目标潜在变量的分布,旨在解决训练和测试条件之间的声学不匹配。先验知识传递是通过Variational Bayes(VB)实现的。此外,我们还研究了基于最大后验概率(MAP)的贝叶斯自适应。 在音频场景分类设备的实验结果表明,我们提出的方法在目标设备上可以获得很好的改进,并且 consistently优于其他削减算法。
URL
https://arxiv.org/abs/2401.13766