Submodular Rank Aggregation on Score-based Permutations for Distributed Automatic Speech Recognition
This work addresses the challenge of improving accuracy in distributed ASR systems, which is incremental as it builds on existing aggregation methods with a novel approach.
The paper tackles the problem of aggregating outputs from distributed deep neural network models in automatic speech recognition by using submodular functions for rank aggregation on score-based permutations, resulting in higher speech recognition accuracy compared to traditional methods like Adaboost.
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}.