Abstract: Disclosed is an apparatus and method for augmenting training data using a notch filter. The method may include obtaining original data, and obtaining training data having a modified frequency component from the original data by filtering the original data using a filter configured to remove a component of a predetermined frequency band.

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: Disclosed is a method and apparatus for label encoding in a multi-sound event interval. The method includes identifying an event interval in which a plurality of sound events occurs in a sound signal, separating a sound source into sound event signals corresponding to each sound event by performing sound source separation on the event interval, determining energy information for each of the sound event signals, and performing label encoding based on the energy information.

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 substrate polishing system includes: a polishing machine and a substrate transporter. The polishing machine includes: a lower surface plate to which a substrate is mounted, and an upper surface plate which faces the lower surface plate and polishes the substrate in cooperation with the lower surface plate, the upper surface plate having a larger area than the substrate mounted on the lower surface plate. The substrate transporter is adjacent to the polishing machine and commonly transports the substrate to and from the polishing machine in a first direction, attaches the substrate to the lower surface plate before polishing thereof, and separates from the lower surface plate the substrate after polishing thereof.

Abstract: Disclosed is an apparatus and method for augmenting training data using a notch filter. The method may include obtaining original data, and obtaining training data having a modified frequency component from the original data by filtering the original data using a filter configured to remove a component of a predetermined frequency band.

Abstract: A sound event detection method includes receiving a sound signal and determining and outputting whether a sound event is present in the sound signal by applying a trained neural network to the received sound signal, and performing post-processing of the output to reduce an error in the determination, wherein the neural network is trained to early stop at an optimal epoch based on a different threshold for each of at least one sound event present in a pre-processed sound signal. That is, the sound event detection method may detect an optimal epoch to stop training by applying different characteristics for respective sound events and improve the sound event detection performance based on the optimal epoch.

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: 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: Disclosed is a content processing method including receiving content including broadcast data and advertisement data into which additional information is inserted, extracting the additional information from the advertisement data, identifying the advertisement data from the content based on the extracted additional information, and extracting the broadcast data excluding the advertisement data identified from the content, wherein the additional information is inserted at at least one of optimal intervals determined based on test additional information inserted at a plurality of analysis intervals of an audio signal associated with the advertisement data.

Abstract: Provided are a signal processing method for determining an audience rating of media, and an additional information inserting apparatus, a media reproducing apparatus and an audience rating determining apparatus for performing the same method. In detail, the signal processing method for determining an audience rating of media is a method that may determine an audience rating of media with respect to a whole section of an audio signal by inserting additional information into a silence section through a noise signal.

Abstract: Provided are a signal processing method for determining an audience rating of media, and an additional information inserting apparatus, a media reproducing apparatus and an audience rating determining apparatus for performing the same method. In detail, the signal processing method for determining an audience rating of media is a method that may determine an audience rating of media with respect to a whole section of an audio signal by inserting additional information into a silence section through a noise signal.

Abstract: A method of detecting a sound event includes receiving sound signals using one or more directional microphones, extracting a time interval of each of the sound signals, extracting time information and an azimuth of a sound event included in the sound signals during the extracted time interval, mixing the sound signals received from the directional microphones using the extracted time interval, and determining a direction of the sound event generated at a specific time from a mixed sound signal obtained through the mixing using the extracted time information and azimuth of the sound event.

Abstract: Disclosed is a content processing method including receiving content including broadcast data and advertisement data into which additional information is inserted, extracting the additional information from the advertisement data, identifying the advertisement data from the content based on the extracted additional information, and extracting the broadcast data excluding the advertisement data identified from the content, wherein the additional information is inserted at at least one of optimal intervals determined based on test additional information inserted at a plurality of analysis intervals of an audio signal associated with the advertisement data.

Abstract: Disclosed is a bitstream generation method performed by an acoustic data transmission (ADT) encoder, the method including receiving a first audio signal, receiving additional information converted into a bitstream, and transmitting a second audio signal obtained by inserting the bitstream into the first audio signal, to an ADT decoder.

Abstract: Provided is a method and apparatus for synthesizing a separated sound source, the method including generating spatial information associated with a sound source included in a frame of a stereo audio signal, and synthesizing a separated frequency-domain sound source from the frame of the stereo audio signal based on the spatial information, wherein the spatial information includes a frequency-azimuth plane representing an energy distribution corresponding to a frequency and an azimuth of the frame of the stereo audio signal.

Abstract: Provided is an apparatus and method for creating multilingual audio content based on a stereo audio signal. The method of creating multilingual audio content including adjusting an energy value of each of a plurality of sound sources provided in multiple languages, setting an initial azimuth angle of each of the sound sources based on a number of the sound sources, mixing each of the sound sources to generate a stereo signal based on the set initial azimuth angle, separating the sound sources to play the mixed sound sources using a sound source separating algorithm, and storing the mixed sound sources based on a sound quality of each of the separated sound sources.

Abstract: Provided is a tag insertion method performed by an apparatus for inserting a tag into a stereo audio signal, the method including receiving an original stereo audio signal, analyzing an energy distribution of the original stereo audio signal based on an azimuth, determining valid azimuths for control information and for a plurality of pieces of tag information based on the energy distribution, wherein the control information is used to control tag information, modulating the plurality of pieces of tag information and the control information generated based on the valid azimuths, generating a left signal and a right signal based on the modulated control information and the plurality of pieces of modulated tag information, and generating a multi-tagged stereo audio signal by mixing the generated left signal and the generated right signal with the original stereo audio signal.

Abstract: A substrate polishing system includes: a polishing machine and a substrate transporter. The polishing machine includes: a lower surface plate to which a substrate is mounted, and an upper surface plate which faces the lower surface plate and polishes the substrate in cooperation with the lower surface plate, the upper surface plate having a larger area than the substrate mounted on the lower surface plate. The substrate transporter is adjacent to the polishing machine and commonly transports the substrate to and from the polishing machine in a first direction, attaches the substrate to the lower surface plate before polishing thereof, and separates from the lower surface plate the substrate after polishing thereof.