We investigate multilingual modeling in the context of a deep neural network (DNN)-hidden
Markov model (HMM) hybrid, where the DNN outputs are used as the HMM state likelihoods …

We have made significant progress in automatic speech recognition ASR for well-defined
applications like dictation and medium vocabulary transaction processing tasks in relatively …

Recently there has been interest in the approaches for training speech recognition systems
for languages with limited resources. Under the IARPA Babel program such resources have …

Automatic speech recognition (ASR) systems are beginning to appear in a wide variety of
information systems. In automobiles or in miniature cellular phones, ASR allows users to …

We propose a multitask learning (MTL) approach to improve low-resource automatic speech
recognition using deep neural networks (DNNs) without requiring additional language …

This paper documents and describes the criteria used to select languages for study within
programs that include low resource languages whether given that label or another similar …

We study key issues related to multilingual acoustic modeling for automatic speech
recognition (ASR) through a series of large-scale ASR experiments. Our study explores …

The development of high-performance speech processing systems for low-resource
languages is a challenging area. One approach to address the lack of resources is to make …