Personal tools
You are here: Home MLMI workshops MLMI'07
Document Actions

MLMI'07 - day 1

last modified 2008-01-09 18:38
MLMI 07 workshop

keyword examples:
hmm, speech, ami corpus
face, interaction, meeting





This page is the result of a capture system developped in the framework of IM2 and AMI.


Opening remarks [0h08]
Andrei Popescu-Belis (ISSCO University of Geneva - Switzerland), Honza Cernocky (University of Brno - Czech republic)
Download & play
Download video video+slides (58MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (3MB)








...

Using Prosodic Features in Language Models for Meetings [0h29]
Songfang Huang and Steve Renals (University of Edinburgh, UK)
Download & play
Download video video+slides (195MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (11MB)








...

Posterior-Based Features and Distances in Template Matching for Speech Recognition [0h17]
Guillermo Aradilla and Herve Bourlard, presented by Mathew Magimai Doss (IDIAP, Switzerland)
Download & play
Download video video+slides (70MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (7MB)








...

A Study of Phoneme and Grapheme Based Context-dependent ASR Systems [0h25]
John Dines and Mathew Magimai Doss (IDIAP, Switzerland)
Download & play
Download video video+slides (191MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (10MB)








...

How to follow a conversation without listening to the words [0h48]
Nick Campbell (Media Information Science Laboratories, ATR, Japan)
Download & play
Download video video+slides (344MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (19MB)








...

Automatic Labeling Inconsistencies Detection And Correction for Sentence Unit Segmentation in Conversational Speech [0h22]
Sebastien Cuendet, Dilek Hakkani-Tur and Elizabeth Shriberg (EPFL, Switzerland)
Download & play
Download video video+slides (173MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (9MB)








...

Modeling Vocal Interaction for Segmentation in Meeting Recognition [0h29]
Kornel Laskowski and Tanja Schultz (CMU, USA)
Download & play
Download video video+slides (228MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (11MB)








...

Binaural Speech Separation Using Recurrent Timing Neural Networks for Joint F0-Localisation Estimation [0h25]
Stuart Wrigley and Guy Brown (University of Sheffield, UK)
Download & play
Download video video+slides (195MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (10MB)








...

To Separate Speech! A System for Recognizing Simultaneous Speech [0h26]
John McDonough, Kenichi Kumatani, Tobias Gehrig, Emilian Stoimenov, Uwe Mayer, Stefan Schacht, Matthias Woelfel and Dietrich Klakow (University of Karlsruhe, Germany)
Download & play
Download video video+slides (203MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (10MB)








...

A Microphone Array Beamforming Approach to Blind Speech Separation [0h28]
Iain McCowan (CSIRO, Australia), Ivan Himawan and Mike Lincoln (University of Edinburgh, UK)
Download & play
Download video video+slides (219MB)
stream at 150kbps streaming click image to get audio feed RSS

mp3 (11MB)








...

MLMI 2007 Day 2
This page is the result of a capture system developped in the framework of IM2 and AMI.

Flash player VLC video player (for )
Real Player (for )

help about configuring audio/video players (ie. RealPlayer) on Linux / MacOS / Windows

www.klewel.com

Powered by Plone