Submodular Rank Aggregation on Score-based Permutations for Distributed Automatic Speech Recognition

Abstract

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}.

Accepted to ICASSP 2020. Please download the pdf to view Figure 1. arXiv admin note: substantial text overlap with arXiv:1707.01166

References in corpus (2)

• The Lovasz-Bregman Divergence and connections to rank aggregation, clustering, and web ranking
• Unsupervised Submodular Rank Aggregation on Score-based Permutations

Cited by in corpus (3)

• Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech Recognition
• PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
• Variational Inference-Based Dropout in Recurrent Neural Networks for Slot Filling in Spoken Language Understanding