Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Advances in Fast Multistream Diarization based on the Information Bottleneck Framework
 
conference paper

Advances in Fast Multistream Diarization based on the Information Bottleneck Framework

Vijayasenan, Deepu  
•
Valente, Fabio
•
Bourlard, Hervé  
2010
Proceedings of Interspeech

Multistream diarization is an effective way to improve the diarization performance, MFCC and Time Delay Of Arrivals (TDOA) being the most commonly used features. This paper extends our previous work on information bottleneck diarization aiming to include large number of features besides MFCC and TDOA while keeping computational costs low. At first HMM/GMM and IB systems are compared in case of two and four feature streams and analysis of errors is performed. Results on a dataset of 17 meetings show that, in spite of comparable oracle performances, the IB system is more robust to feature weight variations. Then a sequential optimization is introduced that further improves the speaker error by 5 − 8% relative. In the last part, computational issues are discussed. The proposed approach is significantly faster and its complexity marginally grows with the number of feature streams running in 0.75 real time even with four streams achieving a speaker error equal to 6%.

  • Details
  • Metrics
Type
conference paper
DOI
10.21437/Interspeech.2010-703
Author(s)
Vijayasenan, Deepu  
Valente, Fabio
Bourlard, Hervé  
Date Issued

2010

Published in
Proceedings of Interspeech
Start page

2650

End page

2653

URL

Related documents

http://publications.idiap.ch/index.php/publications/showcite/Vijayasenan_Idiap-RR-23-2010
Written at

EPFL

EPFL units
LIDIAP  
Available on Infoscience
November 17, 2010
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/57734
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés