论文标题
分布式自动语音识别的基于得分的排列列表汇总
Submodular Rank Aggregation on Score-based Permutations for Distributed Automatic Speech Recognition
论文作者
论文摘要
分布式自动语音识别（ASR）需要汇总基于分布式深神经网络（DNN）模型的输出。这项工作研究了在基于分数的排列上使用次次功能设计等级聚合，该置换量可用于监督和无监督模式中的分布式ASR系统。具体而言，我们基于Lovasz Bregman差异来组成一个聚合级别函数，用于设置线性结构化凸和嵌套结构化凹形函数。该算法基于随机梯度下降（SGD），可以获得训练有素的聚合模型。我们在分布式ASR系统上的实验表明，比传统的聚合方法（如Adaboost）可以获得表达秩的聚合可以获得更高的语音识别精度。代码可在线获得〜\ footNote {https://github.com/uwjunqi/subrank}。
Distributed automatic speech recognition (ASR) requires to aggregate outputs of distributed deep neural network (DNN)-based models. This work studies the use of submodular functions to design a rank aggregation on score-based permutations, which can be used for distributed ASR systems in both supervised and unsupervised modes. Specifically, we compose an aggregation rank function based on the Lovasz Bregman divergence for setting up linear structured convex and nested structured concave functions. The algorithm is based on stochastic gradient descent (SGD) and can obtain well-trained aggregation models. Our experiments on the distributed ASR system show that the submodular rank aggregation can obtain higher speech recognition accuracy than traditional aggregation methods like Adaboost. Code is available online~\footnote{https://github.com/uwjunqi/Subrank}.
