Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Audio-visual machine perception

Radu HoraudINRIA Grenoble[Home Page]

Notice:  Hosted by Richard Waldinger

Date:  Thursday, October 25th 2018 at 4:00pm

Location:  EK255 (SRI E building)  (Directions)

Join Remotely: 

VTC available - contact me for information.
   Abstract

Visual and audio perception play complementary roles. Vision is used to localize and recognize objects of various kinds while audition forms the basis of spoken communication. This complementarity has a great potential for building computational models, with many interesting applications in human-computer and human-robot interaction. Yet, these two modalities were studied almost independently. In this talk I will first try to characterize visual and audio representations well suited for combining them in a robust way. Then I will describe several audio-visual fusion algorithms well suited for tracking people over time and for characterizing their speaking activities. Finally, I will show that audio-visual perception could be combined with speech recognition and that this opens the door to addressing the challenging problem of multi-party situated dialog.

   Bio for Radu Horaud

Radu Patrice Horaud (PhD’81) holds a position of director of research at INRIA Grenoble, France, since 1998. Previous to that, he was a post-doctoral fellow with the Artificial Intelligence Center of SRI International, Menlo Park CA, from 1982 to 1984, and a research scientist with CNRS Grenoble, France, from 1984 to 1998. Radu’s research interests cover computational vision, audio signal processing, audio-visual scene analysis, machine learning, and robotics. Recently, the European Research Council awarded Radu twice: in 2013 (ERC Advanced Grant VHIA, 2014-2019) and in 2017 (ERC Proof of Concept Grant VHIALab, 2018-2019).

   Note for Visitors to SRI

Please arrive at least 10 minutes early as you will need to sign in by following instructions by the lobby phone at Building E (or call Wilma Lenz at 650 859 4904, or Eunice Tseng at 650 859 2799). SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the parking lots off Fourth Street. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page. There are two entrances to SRI International located on Ravenswood Ave. Please check the Building E entrance signage.

SRI International
©2018 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy