Abstract:
A video processing apparatus includes a memory storing instructions, and at least one processor configured to execute the instructions to generate a plurality of feature information by analyzing a video signal comprising a plurality of images based on a first DNN, extract a first altitude component and a first planar component corresponding to a movement of an object in a video from the video signal based on a second DNN, extract a second planar component corresponding to a movement of a sound source in audio from a first audio signal based on a third DNN, generate a second altitude component based on the first altitude component, the first planar component, and the second planar component, output a second audio signal comprising the second altitude component based on the feature information, and synchronize the second audio signal with the video signal and output the synchronized second audio signal and video signal.
Abstract:
The present disclosure relates to a communication apparatus and method for supporting a forward error correction scheme in a communication system. To this end, by means of a generation mode among a plurality of generation modes (ssbg_mode #0, #1, #2), a source symbol block having a plurality of source symbols is generated by using a source packet block having a plurality of source packets, and a repair symbol block for the generated source symbol block is generated by means of a forward error correction (FEC) scheme among a plurality of FEC schemes (FEC payload ID mode 0, FEC payload ID mode 1). A first FEC scheme (FEC payload ID mode 1) is applied to generate the repair symbol block, and in response to an occurrence of a discontinuity in packet sequence numbers, a repair packet may be generated to include length repair data and a repair FEC payload identifier (ID).
Abstract:
An audio processing apparatus may obtain second audio signals corresponding to channels included in a second channel group from first audio signals corresponding to channels included in a first channel group, downsample at least one third audio signal corresponding to at least one channel identified based on a correlation with the second channel group from among the channels included in the first channel group, by using an artificial intelligence (AI) model, and generate a bitstream including the second audio signals corresponding to the channels included in the second channel group and the downsampled at least one third audio signal. The first channel group includes a channel group of an original audio signal, and the second channel group is constructed by combining at least two channels from among the channels included in the first channel group.
Abstract:
A packet transmission/reception apparatus and method is provided. The packet transmission method of the present invention includes acquiring a source payload including partial source symbols from a source block, generating a source packet including the source payload and an identifier (ID) of the source payload, generating a repair packet including a repair payload corresponding to the source payload and an ID of the repair payload, generating a Forward Error Correction (FEC) packet block including the source and repair packets, and transmitting the FEC packet block. The source payload ID includes a source payload sequence number incrementing by 1 per source packet. The packet transmission/reception method of the present invention is advantageous in improving error correction capability and network resource utilization efficiency.
Abstract:
A packet transmission/reception apparatus and method is provided. The packet transmission method of the present invention includes acquiring a source payload including partial source symbols from a source block, generating a source packet including the source payload and an identifier (ID) of the source payload, generating a repair packet including a repair payload corresponding to the source payload and an ID of the repair payload, generating a Forward Error Correction (FEC) packet block including the source and repair packets, and transmitting the FEC packet block. The source payload ID includes a source payload sequence number incrementing by 1 per source packet. The packet transmission/reception method of the present invention is advantageous in improving error correction capability and network resource utilization efficiency.
Abstract:
A method of matching a voice for each object included in a video, includes: separating a plurality of voices in a video; determining a dissimilarity between the plurality of voices; selecting a partial duration in an entire duration of the video as a matching duration, based on the dissimilarity between the plurality of voices; matching, within the matching duration, the plurality of voices with a plurality of objects in the video respectively, based on mouth movements of the plurality of objects; and matching the plurality of voices with the plurality of objects respectively in the entire duration of the video, based on results of the matching between the plurality of voices and the plurality of objects within the matching duration.
Abstract:
A method and apparatus are provided for recovering data efficiently even when data loss has occurred over a channel or network. The packet transmission method includes arranging a first transmission packet in a source symbol in a first region of a source block; arranging a second transmission packet in a space starting with an empty space of a last source symbol where the first transmission packet is arranged, remaining after arranging the first transmission packet; arranging information related to the second transmission packet in a second region of the source block; performing Forward Error Correction (FEC) encoding on the source block; and transmitting the encoded source block.
Abstract:
A packet transmission/reception method for use in a communication system is provided. The method includes generating control information corresponding to Forward Error Correction (FEC), acquiring at least one source packet to be protected using the FEC, generating at least one repair symbol with at least one repair FEC payload ID and at least one source FEC payload ID according to the at least one source packet and the control information, and transmitting the at least one source packet, the at least one repair symbol with the at least one repair FEC payload ID, and the at least one source FEC payload ID.
Abstract:
A packet transmission/reception apparatus and method is provided. The packet transmission method of the present invention includes acquiring a source payload including partial source symbols from a source block, generating a source packet including the source payload and an identifier (ID) of the source payload, generating a repair packet including a repair payload corresponding to the source payload and an ID of the repair payload, generating a Forward Error Correction (FEC) packet block including the source and repair packets, and transmitting the FEC packet block. The source payload ID includes a source payload sequence number incrementing by 1 per source packet. The packet transmission/reception method of the present invention is advantageous in improving error correction capability and network resource utilization efficiency.
Abstract:
A method and device for efficiently transmitting a plurality of pictures are provided. Also, provided are a method and device for efficiently receiving a plurality of transmitted pictures. Provided is a picture transmitting method including obtaining a plurality of input pictures, generating a packed picture by combining the plurality of input pictures based on a packing structure, and generating and transmitting a bitstream including packing structure information and the packed picture.