Unsupervised adaptation of deep neural networks for sound source localization using entropy minimization
Unsupervised adaptation of deep neural networks for sound source localization using entropy minimization
复制标题
DOI：
10.1109/icassp.2017.7952550
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Ryu Takeda;Kazunori Komatani
中科院分区：
文献类型：
--
作者：
Ryu Takeda;Kazunori Komatani
本文描述了一种将深度神经网络（DNN）用于声源定位（SSL）的无监督方法。基于DNNs的SSL对于类似于训练数据的声音数据实现了高定位精度。然而，如果声源处于未知混响环境中的未知位置，则精度劣化。我们通过使用DNN参数对观察到的声音信号的无监督自适应来解决这个问题。在梯度法的基础上，以熵为目标函数，采用最小化方法对参数进行优化。无过拟合的自适应通过使用1）参数自适应层（诸如线性变换网络）和2）参数更新的早期停止来实现。实验结果表明，我们的方法提高了定位精度的未知位置和混响数据的最多20点。
This paper describes an unsupervised method of adapting deep neural networks (DNNs) for sound source localization (SSL). DNNs-based SSL achieves high localization accuracy for sound data that are similar to training data. However, the accuracy deteriorates if a sound source is at an unknown position in unknown reverberant environments. We solve the problem by using unsupervised adaption of the DNNs' parameters to the observed sound signals. Entropy is used as the objective function and minimized to optimize the parameters on the basis of the gradient method. Adaptation without overfitting is achieved by using 1) a parameter adaptation layer, such as linear transform network, and 2) early stopping of the parameter updates. Experimental results indicated that our method improved localization accuracy by a maximum of 20 points for unknown positions and reverberant data.