This paper investigates data augmentation for deep neural network acoustic modeling
based on label-preserving transformations to deal with data sparsity. Two data …

US9196243B2 - Method and system for efficient spoken term detection using confusion
networks - Google Patents US9196243B2 - Method and system for efficient spoken term …

Spoken content retrieval refers to directly indexing and retrieving spoken content based on
the audio rather than text descriptions. This potentially eliminates the requirement of …

This paper examines the impact of multilingual (ML) acoustic representations on Automatic
Speech Recognition (ASR) and keyword search (KWS) for low resource languages in the …

In recent years, so-called,“end-to-end” speech recognition systems have emerged as viable
alternatives to traditional ASR frameworks. Keyword search, localizing an orthographic …

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 …

Spoken content in languages of emerging importance needs to be searchable to provide
access to the underlying information. In this paper, we investigate the problem of extending …

Deep neural networks (DNNs) are constructed by considering highly complicated
configurations including network structure and several tuning parameters (number of hidden …

This paper presents the progress of acoustic models for lowresourced languages
(Assamese, Bengali, Haitian Creole, Lao, Zulu) developed within the second evaluation …

This paper addresses the robust speech recognition problem as an adaptation task.
Specifically, we investigate the cumulative application of adaptation methods. A bidirectional …