Method and apparatus for obtaining audio-visual information, device, and storage medium

An apparatus for obtaining audio-visual information, the apparatus comprising:

• a video and audio obtaining circuit configured to obtain original video information and original audio information corresponding to respective speakers during a conversation;
• a frame sequence extracting circuit configured to extract, based on the original audio information, a video frame sequence of a speaker who is speaking in each of the original video information;
• a frame sequence stitching circuit configured to stitch each of the extracted video frame sequences in a chronological order to obtain stitched video information;
• and
• an audio-visual information obtaining circuit configured to match the stitched video information with the original audio information to obtain the audio-visual information.

An audio-visual information obtaining device, comprising:

• a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the following is implemented when the processor executes the program:
• obtaining original video information and original audio information corresponding to respective speakers during a conversation;
• extracting, based on the original audio information, a video frame sequence of a speaker who is speaking in each of the original video information;
• stitching each of the extracted video frame sequences in a chronological order to obtain stitched video information;
• and
• matching the stitched video information with the original audio information to obtain the audio-visual information.