Publication

Nonlinear feature transformations for noise robust speech recognition

Publications associées (91)

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

On Spectral Methods and the Structuring of Home Videos

Daniel Gatica-Perez, Jean-Marc Odobez

Accessing and organizing home videos present technical challenges due to their unrestricted content and lack of storyline. In this paper, we propose a spectral method to group video shots into scenes based on their visual similarity and temporal relations. ...

IDIAP2002

Real-time spectral imaging in three spatial dimensions

Demetri Psaltis, Wei Liu

We report what is to our knowledge the first volume-holographic optical imaging instrument with the capability to return three-dimensional spatial as well as spectral information about semitranslucent microscopic objects in a single measurement. The four-d ...

2002

Speech Recognition Using Advanced HMM2 Features

Hervé Bourlard, Samy Bengio, Katrin Weber

HMM2 is a particular hidden Markov model where state emission probabilities of the temporal (primary) HMM are modeled through (secondary) state-dependent frequency-based HMMs [12]. As shown in [13], a secondary HMM can also be used to extract robust ASR fe ...

IDIAP2001

Speech Recognition Using Advanced HMM2 Features

Hervé Bourlard, Samy Bengio, Katrin Weber

2001

Robust Speech Recognition and Feature Extraction Using HMM2

Hervé Bourlard, Samy Bengio, Katrin Weber, Shajith Ikbal

This paper presents the theoretical basis and preliminary experimental results of a new HMM model, referred to as HMM2, which can be considered as a mixture of HMMs. In this new model, the emission probabilities of the temporal (primary) HMM are estimated ...

IDIAP2001

Spectral processing of point-sampled geometry

Mark Pauly

We present a new framework for processing point-sampled objects using spectral methods. By establishing a concept of local frequencies on geometry, we introduce a versatile spectral representation that provides a rich repository of signal processing algori ...

2001

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

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 all this data become of crucial importance. Machine learning tries to develop models which can make the information load accessible. Thre ...

IDIAP2000

Mixture Models for Unsupervised and Supervised Learning

École Polytechnique Fédérale de Lausanne, Computer Science Department2000

Multi-Stream Speech Recognition

Hervé Bourlard

In this paper, we discuss a new automatic speech recognition (ASR) approach based on independent processing and recombination of several feature streams. In this framework, it is assumed that the speech signal is represented in terms of multiple input stre ...

IDIAP1996