Publications related to Identifying unexpected words using in-context and out-of-context phoneme posteriors

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

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

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

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

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

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

, ,

In this paper, we further investigate the large vocabulary continuous speech recognition approach to keyword spotting. Given a speech utterance, recognition is performed to obtain a word lattice. The posterior probability of keyword hypotheses in the latti ...

IDIAP2007

On Confusions in a Phoneme Recognizer

Hynek Hermansky, Joel Praveen Pinto

In this paper, we analyze the confusions patterns at three places in the hybrid phoneme recognition system. The confusions are analyzed at the pronunciation, the posterior probability, and the phoneme recognizer levels. The confusions show significant stru ...

2007

On Confusions in a Phoneme Recognizer

Hynek Hermansky, Joel Praveen Pinto

In this paper, we analyze the confusions patterns at three places in the hybrid phoneme recognition system. The confusions are analyzed at the pronunciation, the posterior probability, and the phoneme recognizer levels. The confusions show significant stru ...

IDIAP2007

Identifying unexpected words using in-context and out-of-context phoneme posteriors

Graph Chatbot

Chat with Graph Search

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

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

Support Vector Machines with a Reject Option

Acoustic Models for Posterior Features in Speech Recognition

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

On Confusions in a Phoneme Recognizer

On Confusions in a Phoneme Recognizer

Support Vector Machines with a Reject Option

On Confusions in a Phoneme Recognizer

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

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

Acoustic Models for Posterior Features in Speech Recognition

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

On Confusions in a Phoneme Recognizer