In this invited paper, my overview material on the same topic as presented in the plenary
overview session of APSIPA-2011 and the tutorial material presented in the same …

Over the past decade or so, several advances have been made to the design of modern
large vocabulary continuous speech recognition (LVCSR) systems to the point where their …

Training neural network acoustic models with sequencediscriminative criteria, such as state-
level minimum Bayes risk (sMBR), been shown to produce large improvements in …

This paper seeks to close the gap between training algorithms used in statistical machine
translation and machine learning, specifically the framework of empirical risk minimization …

There is a vast body of literature on LVCSR research and some limitation is necessary in the
scope of this article. We will focus primarily on the techniques that have been successful in …

Speech recognition is a kind of technology that is using computer to transfer the voice signal
to an associated text or command by identification and understand. The paper depicts the …

We introduce a model that maps variablelength word utterances to a word vector space
using convolutional neural networks. Convolutional networks are a rich class of architecture …

We describe our work on developing a speech recognition system for multi-genre media
archives. The high diversity of the data makes this a challenging recognition task, which may …

Automatic speech recognition (ASR) systems classify structured sequence data, where the
label sequences (sentences) must be inferred from the observation sequences (the acoustic …

In recent years, the use of morphological decomposition strategies for Arabic Automatic
Speech Recognition (ASR) has become increasingly popular. Systems trained on …