English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse
  1. Start / 
  2. Item Summary / 
  3. View item

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Motion history images for online speaker/signer diarization

Gebre, B. G., Wittenburg, P., Heskes, T., & Drude, S. (2014). Motion history images for online speaker/signer diarization. In Proceedings of the 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 1537-1541). Piscataway, NJ: IEEE.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0015-1AC4-2 Version Permalink: https://hdl.handle.net/21.11116/0000-0004-8535-A
Genre: Conference Paper

Files

show Files
hide Files
:
gebre_etal_2014.pdf (Publisher version), 206KB
 
File Permalink:
-
Name:
gebre_etal_2014.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Gebre, Binyam Gebrekidan1, Author           
Wittenburg, Peter1, Author           
Heskes, Tom2, Author
Drude, Sebastian1, Author           
Affiliations:
1The Language Archive, MPI for Psycholinguistics, Max Planck Society, ou_530892              
2Radboud University, ou_persistent22              

Content

show
hide
Free keywords: speaker diarization, signer diarization
 Abstract: We present a solution to the problem of online speaker/signer diarization - the task of determining "who spoke/signed when?". Our solution is based on the idea that gestural activity (hands and body movement) is highly correlated with uttering activity. This correlation is necessarily true for sign languages and mostly true for spoken languages. The novel part of our solution is the use of motion history images (MHI) as a likelihood measure for probabilistically detecting uttering activities. MHI is an efficient representation of where and how motion occurred for a fixed period of time. We conducted experiments on 4.9 hours of a publicly available dataset (the AMI meeting data) and 1.4 hours of sign language dataset (Kata Kolok data). The best performance obtained is 15.70% for sign language and 31.90% for spoken language (measurements are in DER). These results show that our solution is applicable in real-world applications like video conferences.

Details

show
hide
Language(s): eng - English
 Dates: 2012-11-042014-02-032014
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1109/ICASSP.2014.6853855
 Degree: -

Event

show
hide
Title: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2014
Place of Event: FLORENCE, ITALY
Start-/End Date: 2014-05-04 - 2014-05-09

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1537 - 1541 Identifier: -