Publication

Low-Dimensional Motion Features for Audio-Visual Speech Recognition

Related publications (47)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Audio?Visual Synchronisation for Speaker Diarisation

Hervé Bourlard

The role of audio–visual speech synchrony for speaker diarisation is investigated on the multiparty meeting domain. We measured both mutual information and canonical correlation on different sets of audio and video features. As acoustic features we conside ...

2010

Semi-supervised Extraction of Audio-Visual Sources

Patricia Calatayud Martinez

This report presents a semi-supervised method to jointly extract audio-visual sources from a scene. It consist of applying a supervised method to segment the video signal followed by an automatic process to properly separate the audio track. This approach ...

2010

Overcoming Asynchrony in Audio-Visual Speech Recognition

Jean-Philippe Thiran, Virginia Estellers Casas

In this paper we propose two alternatives to overcome the natural asynchrony of modalities in Audio-Visual Speech Recognition. We first investigate the use of asynchronous statistical models based on Dynamic Bayesian Networks with different levels of async ...

2010

Bridging the Gap between Detection and Tracking for 3D Human Motion Recovery

Andrea Fossati

The aim of this thesis is to build a system able to automatically and robustly track human motion in 3–D starting from monocular input. To this end two approaches are introduced, which tackle two different types of motion: The first is useful to analyze ac ...

EPFL2010

A learning by imitation model handling multiple constraints and motion alternatives

Aude Billard, Sylvain Calinon, Eric Sauser, Florent D'Halluin

We present a probabilistic approach to learn robust models of human motion through imitation. The association of Hidden Markov Model (HMM), Gaussian Mixture Regression (GMR) and dynamical systems allows us to extract redundancies across multiple demonstrat ...

2010

Encoder and Decoder Side Global and Local Motion Estimation for Distributed Video Coding

Touradj Ebrahimi, Frédéric Dufaux

In this paper, we propose a new Distributed Video Coding (DVC) architecture where motion estimation is performed both at the encoder and decoder, effectively combining global and local motion models. We show that the proposed approach improves significantl ...

2010

Audio-based nonlinear video diffusion

Pierre Vandergheynst, Anna Llagostera Casanovas

We propose a novel non-linear video diffusion approach which is able to focus on parts of a video sequence that are relevant for applications in audio-visual analysis. The diffusion process is controlled by a diffusion coefﬁcient based on an estimate of th ...

2010

Estimating Dominance in Multi-Party Meetings Using Speaker Diarization

Daniel Gatica-Perez, Yan Huang

With the increase in cheap commercially available sensors, recording meetings is becoming an increasingly practical option. With this trend comes the need to summarize the recorded data in semantically meaningful ways. Here, we investigate the task of auto ...

2010

Multimodal feature extraction and fusion for audio-visual speech recognition

Mihai Gurban

Multimodal signal processing analyzes a physical phenomenon through several types of measures, or modalities. This leads to the extraction of higher-quality and more reliable information than that obtained from single-modality signals. The advantage is two ...

EPFL2009

When motion takes form

Manuel Mercier

When and where is visual motion processed in the human brain? This question is highly relevant considering the importance of motion for our perception of the dynamical world surrounding us. In the present work we studied motion processing, firstly through ...

EPFL2009