Publication

Multi-stream ASR: An Oracle Perspective

Publications associées (40)

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

Towards Explaining the Success (Or Failure) of Fusion in Biometric Authentication

Samy Bengio, Norman Hoon Thian Poh

Biometric authentication is a process of verifying an identity claim using a person's behavioral and physiological characteristics. Due to vulnerability of the system to environmental noise and variation caused by the user, fusion of several biometric-enab ...

IDIAP2005

Multi-stream ASR: Oracle Test and Embedded Training

Hervé Bourlard, Hemant Misra

Multi-stream based automatic speech recognition (ASR) systems outperform their single stream counterparts, especially in the case of noisy speech. However, the main issues in multi-stream systems are to know a) Which streams to be combined, and b) How to c ...

IDIAP2005

Image Replica Detection based on Binary Support Vector Classifier

Touradj Ebrahimi

In this paper, we present a system for image replica detection. More specifically, the technique is based on the extraction of 162 features corresponding to texture, color and gray-level characteristics. These features are then weighted and statistically n ...

2005

Boosting HMMs with an application to speech recognition

Samy Bengio, Christos Dimitrakakis

Boosting is a general method for training an ensemble of classifiers with a view to improving performance relative to that of a single classifier. While the original AdaBoost algorithm has been defined for classification tasks, the current work examines it ...

2004

Boosting HMMs with an application to speech recognition

Samy Bengio, Christos Dimitrakakis

2004

New Entropy Based Combination Rules in HMM/ANN Multi-stream ASR

Hervé Bourlard, Hemant Misra, Vivek Tyagi

Classifier performance is often enhanced through combining multiple streams of information. In the context of multi-stream HMM/ANN systems in ASR, a confidence measure widely used in classifier combination is the entropy of the posteriors distribution outp ...

2003

From error probability to information theoretic signal and image processing

Torsten Butz

The signal processing community is increasingly interested in using information theoretic concepts to build signal processing algorithms for a variety of applications. A general theory on how to apply the mathematical concepts of information theory to the ...

EPFL2003

Boosting HMMs with an application to speech recognition

Samy Bengio, Christos Dimitrakakis

IDIAP2003

Entropy-based Multi-stream Combination

Hervé Bourlard, Hemant Misra, Vivek Tyagi

Full-combination multi-band approach has been proposed in the literature and performs well for band-limited noise. But the approach fails to deliver in case of wide-band noise. To overcome this, multi-stream approaches are proposed in literature with varyi ...

IDIAP2002

Mixture models for unsupervised and supervised learning

In a society which produces and consumes an ever increasing amount of information, methods which can make sense out of al1 this data become of crucial importance. Machine learning tries to develop models which can make the information load accessible. Thre ...

EPFL2000