Search

Madjid S Mousavi

from Lawrenceville, NJ
Age ~64

Madjid Mousavi Phones & Addresses

  • 7 Registry Rd, Lawrence Twp, NJ 08648 (732) 580-7167
  • Lawrenceville, NJ
  • Clemson, SC
  • 7 Liberty Ct, Howell, NJ 07731 (732) 901-1637 (732) 905-5178

Publications

Us Patents

Content Identification System

View page
US Patent:
20050027766, Feb 3, 2005
Filed:
Jul 29, 2003
Appl. No.:
10/629486
Inventors:
Jan Ben - Lawrenceville NJ, US
Christopher Burges - Bellevue WA, US
Madjid Mousavi - Howell NJ, US
Craig Nohl - Middletown NJ, US
International Classification:
G06F017/10
US Classification:
708300000
Abstract:
The content of a media program is recognized by analyzing its audio content to extract therefrom prescribed features, which are compared to a database of features associated with identified content. The identity of the content within the database that has features that most closely match the features of the media program being played is supplied as the identity of the program being played. The features are extracted from a frequency domain version of the media program by a) filtering the coefficients to reduce their number, e.g., using triangular filters; b) grouping a number of consecutive outputs of triangular filters into segments; and c) selecting those segments that meet prescribed criteria, such as those segments that have the largest minimum segment energy with prescribed constraints that prevent the segments from being too close to each other. The triangular filters may be log-spaced and their output may be normalized.

Content Identification System

View page
US Patent:
20150134329, May 14, 2015
Filed:
Nov 11, 2014
Appl. No.:
14/538450
Inventors:
- Murray Hill NJ, US
Christopher J. Burges - Bellevue WA, US
Madjid S. Mousavi - Lawrenceville NJ, US
Craig R. Nohl - Middletown NJ, US
Assignee:
Alcatel-Lucent USA Inc. - Murray Hill NJ
International Classification:
G10L 25/48
G11B 27/11
G11B 27/28
US Classification:
704231
Abstract:
The content of a media program is recognized by analyzing its audio content to extract therefrom prescribed features, which are compared to a database of features associated with identified content. The identity of the content within the database that has features that most closely match the features of the media program being played is supplied as the identity of the program being played. The features are extracted from a frequency domain version of the media program by a) filtering the coefficients to reduce their number, e.g., using triangular filters; b) grouping a number of consecutive outputs of triangular filters into segments; and c) selecting those segments that meet prescribed criteria, such as those segments that have the largest minimum segment energy with prescribed constraints that prevent the segments from being too close to each other. The triangular filters may be log-spaced and their output may be normalized.
Madjid S Mousavi from Lawrenceville, NJ, age ~64 Get Report