Abstract:
Disclosed is a method of providing a video contents service including calculating conversion information indicating a relation between a projection area and an area corresponding to the projection area in order to project video contents on the area corresponding to the projection area which is a partial area within a prepared image in a user image photographed by a user terminal; and transmitting the calculated conversion information to the user terminal.
Abstract:
A method and apparatus for generating late reverberation are provided. The method includes generating a reverberation parameter required to generate late reverberation based on an early room impulse response, outputting late reverberation based on the reverberation parameter, and outputting a room impulse response based on the early room impulse response and the late reverberation.
Abstract:
Disclosed are a training method for a learning model for recognizing an acoustic signal, a method of recognizing an acoustic signal using the learning model, and devices for performing the methods. The method of recognizing an acoustic signal using a learning model includes identifying an acoustic signal including an acoustic event or acoustic scene, determining an acoustic feature of the acoustic signal, dividing the determined acoustic feature for each of a plurality of frequency band intervals, and determining the acoustic event or acoustic scene included in the acoustic signal by inputting the divided acoustic features to a trained learning model.
Abstract:
Provided is a sound event recognition method that may improve a sound event recognition performance using a correlation between difference sound signal feature parameters based on a neural network, in detail, that may extract a sound signal feature parameter from a sound signal including a sound event, and recognize the sound event included in the sound signal by applying a convolutional neural network (CNN) trained using the sound signal feature parameter.
Abstract:
A data augmentation method includes extracting one or more basis vectors and coefficient vectors corresponding to sound source data classified in advance into a target class by applying non-negative matrix factorization (NMF) to the sound source data, generating a new basis vector using the extracted basis vectors, and generating new sound source data using the generated new basis vector and the extracted coefficient vectors.
Abstract:
An apparatus for processing metadata includes: a map node defining component configured to define a map node for setting a virtual map; a map overlay node defining component configured to define a map overlay node for setting a layer in which an augmented reality object is to be overlaid on a map set according to the map node; a map marker node defining component configured to define a map marker node for setting a position of the augmented reality object on the map, which is to be overlaid on the layer set according to the map overlay node; a point of interest node defining component configured to set information on a point of interest, which is a position of the augmented reality object on the map; and a controller configured to load the virtual map, the layer, the map marker, and the point of interest.
Abstract:
An audience selection type augmented broadcasting service providing apparatus and method is provided. The audience selection type augmented broadcasting service providing apparatus may include an augmented broadcast producing server to process a production process of augmented contents to provide the augmented broadcasting service, for broadcast contents, a broadcasting server to multiplex and transmit the broadcast contents and metadata for the augmented broadcasting service, and an augmented content receiving terminal to process the augmented contents based on the metadata for the augmented broadcasting service, while playing the broadcast contents.
Abstract:
In a method of receiving augmenting content, broadcast content and augmenting content are received from a broadcast content providing apparatus, metadata related to the broadcast content is interpreted to check an indicator indicating such that augmenting content are applicable, and augmenting content are requested from an augmenting content providing apparatus by using access information of the augmenting content providing apparatus. Thereafter, augmenting content are received from the augmenting content providing apparatus, and augmenting content received in the augmenting content receiving step are synchronized with the broadcast content and output to a temporal/spatial region corresponding to display region information included in the metadata or the display region information is transmitted to a separate output device. Thus, a viewer can conveniently receive area information-based augmenting content in the form of large capacity multimedia including a graphic image or video without having to perform searching.
Abstract:
Disclosed are methods of training an acoustic scene classification model and classifying an acoustic scene and an electronic device for performing the methods. The training method of an acoustic scene classification model includes inputting training data labeled as an acoustic scene to the acoustic scene classification model that is repeatedly trained by using the training data and outputting a first result predicting the acoustic scene, updating the weight of the auxiliary model configured to induce training of the acoustic scene classification model, based on a weight of the acoustic scene classification model and a weight of an auxiliary model in a previous epoch, inputting the training data to the auxiliary model and outputting a second result, calculating a cost function, based on the first result, the second result, and labeling of acoustic data, and updating the weight of the acoustic scene classification model, based on the cost function.
Abstract:
A navigation apparatus for providing a Social Network Service (SNS) information based on augmented reality, a metadata processor, and a metadata processing method. The navigation apparatus includes an image acquirer configured to acquire a real world image in real time, a controller configured to generate a virtual map on a back ground of the real world image and map augmented SNS information to a point of interest (POI) on the virtual map, and an output component configured to display the SNS information mapped to the virtual map on the real world image.