US 11,929,091 B2
Blind detection of binauralized stereo content
Chunmao Zhang, Fremont, CA (US); Lianwu Chen, Beijing (CN); Ziyu Yang, Beijing (CN); Joshua Brandon Lando, San Francisco, CA (US); David Matthew Fischer, San Francisco, CA (US); and Lie Lu, Dublin, CA (US)
Assigned to Dolby Laboratories Licensing Corporation, San Francisco, CA (US)
Filed by Dolby Laboratories Licensing Corporation, San Francisco, CA (US)
Filed on Mar. 1, 2022, as Appl. No. 17/683,662.
Application 17/683,662 is a continuation of application No. 17/050,786, granted, now 11,264,050, previously published as PCT/US2019/028887, filed on Apr. 24, 2019.
Claims priority of provisional application 62/677,829, filed on May 30, 2018.
Claims priority of application No. PCT/CN2018/084757 (WO), filed on Apr. 27, 2018; and application No. 18177821 (EP), filed on Jun. 14, 2018.
Prior Publication US 2022/0366933 A1, Nov. 17, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 25/78 (2013.01); G06N 3/08 (2023.01); G10L 25/30 (2013.01); H04R 5/033 (2006.01); H04R 5/04 (2006.01); H04S 1/00 (2006.01)
CPC G10L 25/78 (2013.01) [G06N 3/08 (2013.01); G10L 25/30 (2013.01); H04R 5/033 (2013.01); H04R 5/04 (2013.01); H04S 1/002 (2013.01); H04R 2420/07 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus for detecting binauralization of an audio signal, the apparatus comprising:
a feature extractor that is configured to receive an input audio signal, and that is configured to extract a plurality of features from the input audio signal;
a classifier that is configured to receive the plurality of features extracted by the feature extractor, that is configured to perform a classification of the plurality of features, and that is configured to generate a result based on the classification, wherein the result indicates a probability that the input audio signal is a binaural signal;
a virtualizer that is configured to receive the input audio signal, and that is configured to perform virtualization on the input audio signal to generate a binaural audio signal; and
a mixer that is configured to receive the input audio signal, the binaural audio signal and the result, and that is configured to generate an output audio signal according to the result,
wherein when the result indicates that the input audio signal is not the binaural signal, the output audio signal corresponds to the binaural audio signal, and
wherein when the result indicates that the input audio signal is the binaural signal, the output audio signal corresponds to the input audio signal.