US 12,340,822 B2
Audio content identification
Guiping Wang, Beijing (CN); and Lie Lu, Dublin, CA (US)
Assigned to Dolby Laboratories Licensing Corporation, San Francisco, CA (US)
Appl. No. 18/022,125
Filed by Dolby Laboratories Licensing Corporation, San Francisco, CA (US)
PCT Filed Aug. 18, 2021, PCT No. PCT/US2021/046454
§ 371(c)(1), (2) Date Feb. 17, 2023,
PCT Pub. No. WO2022/040282, PCT Pub. Date Feb. 24, 2022.
Claims priority of provisional application 63/074,621, filed on Sep. 4, 2020.
Claims priority of application No. PCT/CN2020/109744 (WO), filed on Aug. 18, 2020; and application No. 20200318 (EP), filed on Oct. 6, 2020.
Prior Publication US 2024/0038258 A1, Feb. 1, 2024
Int. Cl. G10L 25/81 (2013.01); G10L 15/02 (2006.01); G10L 15/08 (2006.01)
CPC G10L 25/81 (2013.01) [G10L 15/02 (2013.01); G10L 15/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of audio processing, the method comprising:
receiving an audio signal;
performing feature extraction on the audio signal to extract a plurality of features;
classifying the plurality of features according to a first audio classification model to generate a first set of confidence scores;
classifying the plurality of features according to a second audio classification model to generate a second confidence score;
calculating a steering signal by combining a first confidence score of the first set of confidence scores and a further confidence score of the first set of confidence scores;
calculating a final confidence score according to the steering signal, the first set of confidence scores, and the second confidence score; and
outputting a classification of the audio signal according to the final confidence score.