loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
12th International Conference on Image Analysis and Processing (ICIAP'03)
A Real-Time Text- Independent Speaker Identification System
Mantova, Italy
September 17-September 19
ISBN: 0-7695-1948-2
ASCII Text
x 
 
L. P. Cordella, P. Foggia, C. Sansone, M. Vento, "A Real-Time Text- Independent Speaker Identification System," Image Analysis and Processing, International Conference on, pp. 632, 12th International Conference on Image Analysis and Processing (ICIAP'03), 2003.
 
 
BibTex
x
 
@article{ 10.1109/ICIAP.2003.1234121,
author = {L. P. Cordella and P. Foggia and C. Sansone and M. Vento},
title = {A Real-Time Text- Independent Speaker Identification System},
journal ={Image Analysis and Processing, International Conference on},
volume = {0},
year = {2003},
isbn = {0-7695-1948-2},
pages = {632},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICIAP.2003.1234121},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Image Analysis and Processing, International Conference on
TI - A Real-Time Text- Independent Speaker Identification System
SN - 0-7695-1948-2
SP
EP
A1 - L. P. Cordella,
A1 - P. Foggia,
A1 - C. Sansone,
A1 - M. Vento,
PY - 2003
KW - null
VL - 0
JA - Image Analysis and Processing, International Conference on
ER -
 
L. P. Cordella, Universit? di Napoli "Federico II"
P. Foggia, Universit? di Napoli "Federico II"
C. Sansone, Universit? di Napoli "Federico II"
M. Vento, Universit? di Salerno

The paper presents a real-time speaker identification system based on the analysis of the audio track of a video stream. The system has been employed in the context of automatic video segmentation. It uses features evaluated in both domains of time and frequency. Their combined use significantly improved the performance of the system.

Experiments have been carried on a database extracted from over one hour of television news, including 10 speakers. The obtained results confirm the effectiveness of the approach, showing an error rate less then 1% when the time interval used for identifying a speaker is about 1.5 seconds.

Citation:
L. P. Cordella, P. Foggia, C. Sansone, M. Vento, "A Real-Time Text- Independent Speaker Identification System," iciap, pp.632, 12th International Conference on Image Analysis and Processing (ICIAP'03), 2003
Usage of this product signifies your acceptance of the Terms of Use.