Segmenting and classifying video content using sounds

A system, comprising:

• at least one computing device;
• and
• at least one application executable in the at least one computing device, wherein when executed the at least one application causes the at least one computing device to at least:
• divide audio accompanying a video content item into a plurality of atomic audio segments of a fixed length;
• classify individual ones of the plurality of atomic audio segments as a silent segment or a sound segment;
• generate a plurality of segments of the video content item based at least in part on smoothing adjacent classifications of the plurality of atomic audio segments using a time window;
• and
• select a subset of the plurality of segments that correspond to music segments based at least in part on an audio characteristic of the subset of the plurality of segments.

A method, comprising:

• generating, by at least one computing device, a plurality of segments of a video content item by analyzing audio accompanying the video content item;
• selecting, by the at least one computing device, a subset of the plurality of segments that correspond to music segments based at least in part on an audio characteristic of the subset of the plurality of segments;
• performing face matching on video frames corresponding to individual segments of the subset of the plurality of segments to visually verify whether a cast member associated with a song appears in the video frames;
• and
• generating, by the at least one computing device, a list of segments of the video content item that correspond to the music segments and are confirmed to have at least a threshold number of visually verified portions using the face matching.