Abstract: Proposed is a detachable mooring system for an offshore structure, including a first tension adjuster connected to an offshore structure, and blocking a pulling chain from proceeding from an outlet of a body toward an inlet, a second tension adjuster connected to one end of the pulling chain and blocking the pulling chain from proceeding from an outlet of a body toward an inlet, a mooring chain having a first longitudinal end connected to one surface of the second tension adjuster body and having a second longitudinal end connected to an anchor on the seabed, a first lead rope having one longitudinal end connected to one end of the pulling chain discharged out through the first tension adjuster outlet, and a second lead rope having one longitudinal end connected to the second tension adjuster body.

Abstract: The present invention relates to a speaker diarization technology, and more specifically to, end-to-end speaker diarization system and method through transformer learning having an auxiliary loss-based residual connection to separate speakers by dividing the speakers for time interval, wherein the end-to-end speaker diarization system and method using an auxiliary loss can differentiate and separate speakers through speaker labeling based on the transformer learning using an auxiliary loss even if speaker speeches overlap in a multi-speaker environment.

Abstract: A temperature prediction system may include a data input module configured to receive data related to climate, a prediction module having installed therein a trained model for predicting a temperature based on input data from the data input module, and an output module configured to output temperature information predicted by the prediction module.

Abstract: In accordance with an aspect of the present disclosure, there is provided a method for identifying a type of a vocoder. The method comprises acquiring identification target bitstreams encoded with a voice signal, acquiring, for each of a plurality of vocoders, a probability that each of the plurality of vocoders is related to the identification target bitstreams from the identification target bitstreams, acquiring waveforms for each decoder of each of the plurality of vocoders by inputting the identification target bitstreams to the each decoder of each of the plurality of vocoders, acquiring intelligibility values for each of the waveforms obtained for the each decoder of each of the plurality of vocoders from the waveforms, and determining the type of the vocoder related to the voice signal from the probability and the intelligibility values for each waveform.

Abstract: A data generating apparatus for generating noise environment noisy data is disclosed. The data generating apparatus according to the present application comprises a signal conversion unit configured to convert each of a noisy signal obtained in real environment and an original sound signal for the noisy signal into a noisy signal spectrum and an original sound signal spectrum in a short-time frequency domain; and a noisy signal generation training unit configured to train deep neural network to output the noisy signal spectrum corresponding to each short-time using the original sound signal spectrum as an input.

Abstract: A temperature prediction system may include a data input module configured to receive data related to climate, a prediction module having installed therein a trained model for predicting a temperature based on input data from the data input module, and an output module configured to output temperature information predicted by the prediction module.

Abstract: In accordance with an aspect of the present disclosure, there is provided a method for identifying a type of a vocoder. The method comprises acquiring identification target bitstreams encoded with a voice signal, acquiring, for each of a plurality of vocoders, a probability that each of the plurality of vocoders is related to the identification target bitstreams from the identification target bitstreams, acquiring waveforms for each decoder of each of the plurality of vocoders by inputting the identification target bitstreams to the each decoder of each of the plurality of vocoders, acquiring intelligibility values for each of the waveforms obtained for the each decoder of each of the plurality of vocoders from the waveforms, and determining the type of the vocoder related to the voice signal from the probability and the intelligibility values for each waveform.

Abstract: A data generating apparatus for generating noise environment noisy data is disclosed. The data generating apparatus according to the present application comprises a signal conversion unit configured to convert each of a noisy signal obtained in real environment and an original sound signal for the noisy signal into a noisy signal spectrum and an original sound signal spectrum in a short-time frequency domain; and a noisy signal generation training unit configured to train deep neural network to output the noisy signal spectrum corresponding to each short-time using the original sound signal spectrum as an input.

Abstract: A low frequency ultrasonic communication system includes: a low frequency ultrasonic transmitting apparatus configured to transmit data using a low frequency ultrasonic wave; and a low frequency ultrasonic receiving apparatus configured to recover the data by processing a low frequency ultrasonic reception signal transmitted from the low frequency ultrasonic transmitting apparatus. In communication between the transmitting apparatus and the receiving apparatus, modulation is performed using a DPSK scheme, and FEC coding is used to perform channel coding before the modulation.

Abstract: A frame erasure concealment technique for a bitstream-based feature extractors in a speech recognition system particularly suited for use in a wireless communication system operates to “delete” each frame in which an erasure is declared. The deletions thus reduce the length of the observation sequence, but have been found to provide for sufficient speech recognition based on both single word and “string” tests of the deletion technique.

Abstract: A method of detecting a particular abnormal sound in an environment with background noise is provided. The method includes acquiring a sound from a microphone, separating abnormal sounds from the input sound based on non-negative matrix factorization (NMF), extracting Mel-frequency cepstral coefficient (MFCC) parameters according to the separated abnormal sounds, calculating hidden Markov model (HMM) likelihoods according to the separated abnormal sounds, and comparing the likelihoods of the separated abnormal sounds with a reference value to determine whether or not an abnormal sound has occurred. According to the method, based on NMF, a sound to be detected is compared with ambient noise in a one-to-one basis and classified so that the sound may be stably detected even in an actual environment with multiple noises.

Abstract: The present invention extracts azimuth information on a sound source, read the touch state of a touch screen on which an image is displayed, and enables a sound source having azimuth information corresponding to a place touched on the image to be synthesized so as to be distinguished from other sound sources. According to the present invention, since it is possible to listen to the distinguished sound of a desired location on an image, a user may be provided with more satisfaction.

Abstract: A method includes extracting a difference value through extraction of features of a front audio channel signal and a surround channel of multichannel sound content by setting the front audio channel signal and the surround channel as input and output channel signals, respectively, training a deep neural network (DNN) model by setting the input channel signal and the difference value as an input and an output of the DNN model, respectively, normalizing a frequency-domain signal of the input channel signal by converting the input channel signal into the frequency-domain signal, and extracting estimated difference values by decoding the normalized frequency-domain signal through the DNN model, deriving an estimated spectral amplitude of the surround channel based on the front audio channel signal and the difference value, and deriving an audio signal of a final surround channel by converting the estimated spectral amplitude of the surround channel into the time domain.

Abstract: A low frequency ultrasonic communication system includes: a low frequency ultrasonic transmitting apparatus configured to transmit data using a low frequency ultrasonic wave; and a low frequency ultrasonic receiving apparatus configured to recover the data by processing a low frequency ultrasonic reception signal transmitted from the low frequency ultrasonic transmitting apparatus. In communication between the transmitting apparatus and the receiving apparatus, modulation is performed using a DPSK scheme, and FEC coding is used to perform channel coding before the modulation.

Abstract: A method includes extracting a difference value through extraction of features of a front audio channel signal and a surround channel of multichannel sound content by setting the front audio channel signal and the surround channel as input and output channel signals, respectively, training a deep neural network (DNN) model by setting the input channel signal and the difference value as an input and an output of the DNN model, respectively, normalizing a frequency-domain signal of the input channel signal by converting the input channel signal into the frequency-domain signal, and extracting estimated difference values by decoding the normalized frequency-domain signal through the DNN model, deriving an estimated spectral amplitude of the surround channel based on the front audio channel signal and the difference value, and deriving an audio signal of a final surround channel by converting the estimated spectral amplitude of the surround channel into the time domain.

Abstract: A method of detecting a particular abnormal sound in an environment with background noise is provided. The method includes acquiring a sound from a microphone, separating abnormal sounds from the input sound based on non-negative matrix factorization (NMF), extracting Mel-frequency cepstral coefficient (MFCC) parameters according to the separated abnormal sounds, calculating hidden Markov model (HMM) likelihoods according to the separated abnormal sounds, and comparing the likelihoods of the separated abnormal sounds with a reference value to determine whether or not an abnormal sound has occurred. According to the method, based on NMF, a sound to be detected is compared with ambient noise in a one-to-one basis and classified so that the sound may be stably detected even in an actual environment with multiple noises.

Abstract: Method and device of extending a signal band of a voice or audio signal are provided. The bandwidth extension method includes the steps of: performing a modified discrete cosine transform (MDCT) process on an input signal to generate a first transform signal; generating a second transform signal and a third transform signal on the basis of the first transform signal; generating normalized components and energy components of the first transform signal, the second transform signal, and the third transform signal therefrom; generating an extended normalized component from the normalized components and generating an extended energy component from the energy components; generating an extended transform signal on the basis of the extended normalized component and the extended energy component; and performing an inverse MDCT (IMDCT) process on the extended transform signal.

Abstract: A streaming reproduction device according to the present disclosure includes a decoder for decoding a file transmitted from a library, an image reproduction device for reproducing an image decoded in the decoder, an audio reproduction device for reproducing an audio decoded in the decoder, and a synchronizer for synchronizing image information with audio information to output the synchronized information. In accordance with the present disclosure, regardless of file information and a communication environment, the stereo extension device may be optimally activated, a sound quality may be improved, and stereo may be stably provided under a streaming environment.

Abstract: Disclosed is an apparatus for extending a bandwidth of a sound signal. The apparatus includes a database that stores predetermined training information as a result of at least one of Gaussian mixture model (GMM) training and hidden Markov model (HMM) training; a modified discrete cosine transform (MDCT) transformer that transforms a first band signal through MDCT, a feature extractor that extracts a feature parameter of the first band signal from an MDCT coefficient output from the MDCT transformer; an extender that provides an extended MDCT coefficient for a second band signal based on the MDCT coefficient of the first band signal output from the MDCT transformer, a subband energy estimator that estimates subband energy of the second band signal with reference to information stored in the database based on the feature parameter.

Abstract: A speech analysis apparatus is provided. An F0 extraction part extracts a pitch value from speech information. A spectrum extraction part extracts spectrum information from the speech information. An MVF extraction part extract a maximum voiced frequency and allows boundary information for respectively filtering a harmonic component and a non-harmonic component to be obtained. According to the speech analysis apparatus, speech synthesis apparatus, and speech analysis synthesis system of the present invention, speech that is closer to the original voice and is more natural may be synthesized. Also, speech may be represented with less data capacity.