Publication

Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator

Publications associées (34)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Developing and Enhancing Posterior Based Speech Recognition Systems

Hervé Bourlard, Samy Bengio, Hamed Ketabdar

Local state or phone posterior probabilities are often investigated as local scores (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., ``Tandem'') to improve speech recogni tion systems. In this paper, we present initial results towa ...

2005

Developing and Enhancing Posterior Based Speech Recognition Systems

Hervé Bourlard, Samy Bengio, Hamed Ketabdar

IDIAP2005

A Probabilistic Interpretation of SVMs with an Application to Unbalanced Classification

Samy Bengio

In this paper, we show that the hinge loss can be interpreted as the neg-log-likelihood of a semi-parametric model of posterior probabilities. From this point of view, SVMs represent the parametric component of a semi-parametric model fitted by a maximum a ...

IDIAP2005

A Probabilistic Interpretation of SVMs with an Application to Unbalanced Classification

Samy Bengio

2005

Modelling Auxiliary Features in Tandem Systems

Hervé Bourlard, Shajith Ikbal

Tandem systems transform the cepstral features into posterior probabilities of subword units using artificial neural networks (ANNs), which are processed to form input features for conventional speech recognition systems. They have been shown to perform be ...

2004

Modelling Auxiliary Features in Tandem Systems

Hervé Bourlard, Shajith Ikbal

IDIAP2004

Towards using hierarchical posteriors for flexible automatic speech recognition systems

Hervé Bourlard, Samy Bengio, Bertrand Mesot

Local state (or phone) posterior probabilities are often investigated as local classifiers (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., ``Tandem'') towards improved speech recognition systems. In this paper, we present initial ...

IDIAP2004

On the Combination of Speech and Speaker Recognition

Hervé Bourlard

This paper investigates an approach that maximizes the joint posterior probabil ity of the pronounced word and the speaker identity given the observed data. This probability can be expressed as a product of the posterior probability of the pronounced word ...

IDIAP2003

On the Combination of Speech and Speaker Recognition

Hervé Bourlard

2003

Using posterior probabilities for speech/music discrimination

Automatic speech/music discrimination has been receiving importance recently, for example when large multimedia documents have to be processed by an ASR system, or for indexing and retrieval of such documents. This work presents using outputs of a speech r ...

IDIAP2001