Alibaba Group Holding Limited

Meta Platforms, Inc.

Yun Lei

Ying Zhang

Gang Liu

Yan Zhao

In one embodiment, a method includes receiving a video file. The video file includes a corresponding audio stream. The method further includes accessing the audio stream, and generating, based on the audio stream, a representative vector. The vector has a particular number of dimensions. The method further includes accessing a label-embedding space, which has the same particular number of dimensions, and includes a number of regions that each correspond to a respective label. The method further includes determining a region of the label-embedding space that corresponds to the vector, the determined region corresponding to a particular label. The method further includes associating the particular label with the video file.

Labeling video files using acoustic vectors

Systems and methods are provided for improving audio signal processing by receiving an audio signal; obtaining a plurality of multi-dimensional features based on the audio signal; obtaining a plurality of segment-level representations based on the plurality of multi-dimensional features; obtaining an utterance-level representation based on the plurality of segment-level representations; and recognizing a speaker from the audio signal based on the utterance-level representation.

Growing community of inventors

San Francisco, CA, United States of America

Yun Lei