US Patent Issued to Huawei Technologies'Co., 'Ltd.' on Feb. 3 for "Audio visual sound source separation with cross-modal meta consistency learning" (Canadian Inventors)

ALEXANDRIA, Va., Feb. 3 -- United States Patent no. 12,542,140, issued on Feb. 3, was assigned to Huawei Technologies'Co.'Ltd.' (Shenzhen, China).

"Audio visual sound source separation with cross-modal meta consistency learning" was invented by Md Amirul Islam (Toronto), Seyed Shahabeddin Nabavi (Toronto), Irina Kezele (North York, Canada), Yang Wang (Winnipeg, Canada), Yuanhao Yu (Markham, Canada) and Jin Tang (Markham, Canada).

According to the abstract* released by the U.S. Patent & Trademark Office: "System, method and/or computer readable medium for audio visual sound source Separation that applies cross-modal meta consistency learning. Inputs include an audio spectrogram that represents first sounds second sounds, a first video of a...