Publications related to Low-Rank Representation For Enhanced Deep Neural Network Acoustic Models

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

We present a framework to apply Volterra series to analyze multilayered perceptrons trained to estimate the posterior probabilities of phonemes in automatic speech recognition. The identified Volterra kernels reveal the spectro-temporal patterns that are l ...

2009

Support Vector Machines with a Reject Option

We consider the problem of binary classification where the classfier may abstain instead of classifying each observation. The Bayes decision rule for this setup, known as Chow’s rule, is deﬁned by two thresholds on posterior probabilities. From simple desi ...

Idiap2009

Acoustic models for posterior features in speech recognition

Guillermo Aradilla

In this thesis, we investigate the use of posterior probabilities of sub-word units directly as input features for automatic speech recognition (ASR). These posteriors, estimated from data-driven methods, display some favourable properties such as increase ...

EPFL2008

Acoustic Models for Posterior Features in Speech Recognition

Guillermo Aradilla

In this thesis, we investigate the use of posterior probabilities of sub-word units directly as input features for automatic speech recognition (ASR). These posteriors, estimated from data-driven methods, display some favourable properties such as increase ...

Ecole Polytechnique Fédérale de Lausanne2008

Acoustic Models for Posterior Features in Speech Recognition

Guillermo Aradilla

In this thesis, we investigate the use of posterior probabilities of sub-word units directly as input features for automatic speech recognition (ASR). These posteriors, estimated from data-driven methods, display some favourable properties such as increase ...

Idiap2008

Using KL-based Acoustic Models in a Large Vocabulary Recognition Task

Hervé Bourlard, Guillermo Aradilla

Posterior probabilities of sub-word units have been shown to be an effective front-end for ASR. However, attempts to model this type of features either do not benefit from modeling context-dependent phonemes, or use an inefficient distribution to estimate ...

IDIAP2008

Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition

Hynek Hermansky, Joel Praveen Pinto

We investigate the use of the log-likelihood of the features obtained from a generative Gaussian mixture model, and the posterior probability of phonemes from a discriminative multilayered perceptron in multi-stream combination for recognition of phonemes. ...

2008

Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition

Hynek Hermansky, Joel Praveen Pinto

We investigate the use of the log-likelihood of the features obtained from a generative Gaussian mixture model, and the posterior probability of phonemes from a discriminative multilayered perceptron in multi-stream combination for recognition of phonemes. ...

IDIAP2008

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

Hynek Hermansky, Joel Praveen Pinto

We present a framework to apply Volterra series to analyze multilayered perceptrons trained to estimate the posterior probabilities of phonemes in automatic speech recognition. The identified Volterra kernels reveal the spectro-temporal patterns that are l ...

Idiap2008

Support Vector Machines with a Reject Option

We consider the problem of binary classification where the classifier may abstain instead of classifying each observation. The Bayes decision rule for this setup, known as Chow’s rule, is deﬁned by two thresholds on posterior probabilities. From simple des ...

2008

Low-Rank Representation For Enhanced Deep Neural Network Acoustic Models

Graph Chatbot

Chat with Graph Search

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

Support Vector Machines with a Reject Option

Acoustic models for posterior features in speech recognition

Acoustic Models for Posterior Features in Speech Recognition

Acoustic Models for Posterior Features in Speech Recognition

Using KL-based Acoustic Models in a Large Vocabulary Recognition Task

Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition

Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

Support Vector Machines with a Reject Option

Acoustic models for posterior features in speech recognition

Support Vector Machines with a Reject Option

Support Vector Machines with a Reject Option

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

Acoustic Models for Posterior Features in Speech Recognition

Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition

Acoustic Models for Posterior Features in Speech Recognition

Using KL-based Acoustic Models in a Large Vocabulary Recognition Task

Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator