Conventional speech recognition systems are based on Gaussian hidden Markov models
(HMMs). Discriminative techniques such as log-linear modeling have been investigated in …

The use of higher-order polynomial acoustic features can improve the performance of
automatic speech recognition (ASR). However, dimensionality of polynomial representation …

Second order polynomial features are useful for speech recognition because they can be
used to model class specific covariance even with a pooled covariance acoustic model …

The use of higher-order polynomial acoustic features can improve the performance of
automatic speech recognition. However, the dimensionality of the polynomial representation …

The discriminative approach to speech recognition offers several advantages over the
generative, such as a simple introduction of additional dependencies and direct modelling of …

Log-linear models have recently been used in acoustic modeling for speech recognition
systems. This has been motivated by competitive results compared to systems based on …

In many pattern recognition problems, learning from training samples is a process that
requires important amounts of training data and a high computational effort. Sometimes, only …

Over the last two decades, large margin methods have yielded excellent performance on
many tasks. The theoretical properties of large margin methods have been intensively …

Discriminative training has been established as an effective technique for training the
acoustic model of an automatic speech recognition system. It reduces the word error rate as …

The use of higher-order polynomial acoustic features can improve the performance of
automatic speech recognition. However, the dimensionality of the polynomial representation …