US 9,812,109 B2
Audio processing techniques for semantic audio recognition and report generation
Alan Neuhauser, Silver Spring, MD (US); and John Stavropoulos, Edison, NJ (US)
Assigned to THE NIELSEN COMPANY (US), LLC, New York, NY (US)
Filed by The Nielsen Company (US), LLC, New York, NY (US)
Filed on Oct. 16, 2015, as Appl. No. 14/885,216.
Application 14/885,216 is a continuation of application No. 13/724,836, filed on Dec. 21, 2012, granted, now 9,195,649.
Prior Publication US 2016/0035332 A1, Feb. 4, 2016
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 25/00 (2013.01); G10H 1/40 (2006.01); G06F 17/28 (2006.01); G10L 19/018 (2013.01); G10L 15/18 (2013.01)
CPC G10H 1/40 (2013.01) [G06F 17/28 (2013.01); G10L 15/1815 (2013.01); G10L 19/018 (2013.01); G10H 2210/036 (2013.01); G10H 2210/066 (2013.01); G10H 2210/071 (2013.01); G10H 2210/076 (2013.01); G10L 15/1822 (2013.01)] 21 Claims
OG exemplary drawing
 
1. An apparatus for forming an audio template for determining semantic audio information, the apparatus comprising:
a processor to:
extract a plurality of audio features from audio, at least one of the plurality of audio features including at least one of a temporal feature, a spectral feature, a harmonic feature, or a rhythmic feature;
determine a range for each of the plurality of audio features; and
store a set of ranges of the plurality of audio features to compare against other audio features from subsequent audio to generate a tag for the set of ranges signifying semantic audio information for the subsequent audio, wherein the set of ranges includes more than one range and the tag is associated with an audio timbre range, a beat range, a loudness range and a spectral histogram range.