Automatic speech recognition (ASR) is one of the most fascinating fields of research and the
performance of ASR systems is most promising in a closed environment having negligible or …

We describe a new approach to speech recognition, in which all Hidden Markov Model
(HMM) states share the same Gaussian Mixture Model (GMM) structure with the same …

We describe an acoustic modeling approach in which all phonetic states share a common
Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of …

Although research has previously been done on multilingual speech recognition, it has been
found to be very difficult to improve over separately trained systems. The usual approach …

The goal of automatic speech recognition (ASR) system is to accurately and efficiently
convert a speech signal into a text message independent of the device, speaker or the …

Speech recognition systems normally use handcrafted pronunciation lexicons designed by
linguistic experts. Building and maintaining such a lexicon is expensive and time …

In automatic speech recognition (ASR) systems, the speech signal is captured and
parameterized at front end and evaluated at back end using the statistical framework of …

This study focuses on acoustic variations in speech introduced by whispering, and proposes
several strategies to improve robustness of automatic speech recognition of whispered …

The Grapheme-to-Phoneme (G2P) task aims to convert orthographic input into a discrete
phonetic representation. G2P conversion is beneficial to various speech processing …

This paper studies cross-lingual acoustic modeling in the context of subspace Gaussian
mixture models (SGMMs). SGMMs factorize the acoustic model parameters into a set that is …