Abstract: A multichannel microphone-based reverberation time estimation method and device which use a deep neural network (DNN) are disclosed. A multichannel microphone-based reverberation time estimation method using a DNN, according to one embodiment, comprises the steps of: receiving a voice signal through a multichannel microphone; deriving a feature vector including spatial information by using the inputted voice signal; and estimating the degree of reverberation by applying the feature vector to the DNN.

Abstract: A noise data artificial intelligence learning method for identifying the source of problematic noise may include a noise data pre-conditioning method for identifying the source of problematic noise including: selecting a unit frame for the problematic noise among noises sampled with time; dividing the unit frame into N segments; analyzing frequency characteristic for each segment of the N segments and extracting a frequency component of each segment by applying Log Mel Filter; and outputting a feature parameter as one representative frame by averaging information on the N segments, wherein an artificial intelligence learning by the feature parameter extracted according to a change in time by the noise data pre-conditioning method applies Bidirectional RNN.

Abstract: Disclosed is a deep neural network-based method and apparatus for combining noise and echo removal. The deep neural network-based method for combining noise and echo removal according to one embodiment of the present invention may comprise the steps of extracting a feature vector from an audio signal that includes noise and echo; and acquiring a final audio signal from which both noise and echo have been removed, by using a combined nose and echo removal gain estimated by means of the feature vector and deep neural network DNN.

Abstract: A multichannel microphone-based reverberation time estimation method and device which use a deep neural network (DNN) are disclosed. A multichannel microphone-based reverberation time estimation method using a DNN, according to one embodiment, comprises the steps of: receiving a voice signal through a multichannel microphone; deriving a feature vector including spatial information by using the inputted voice signal; and estimating the degree of reverberation by applying the feature vector to the DNN.

Abstract: Provided is a speech enhancement method and a system therefor. The speech enhancement method includes receiving at least one speech signal; generating a first speech signal by performing a primary speech enhancement on the at least one speech signal; selecting a noise removing gain corresponding to the first speech signal from pre-learned noise removing gain information; and generating a second speech signal by performing a secondary speech enhancement on the first speech signal based on the selected noise removing gain.

Abstract: Disclosed herein are an apparatus and method for recognizing a voice speaker. The apparatus for recognizing a voice speaker includes a voice feature extraction unit configured to extract a feature vector from a voice signal inputted through a microphone; and a speaker recognition unit configured to calculate a speaker recognition score by selecting a reverberant environment from multiple reverberant environment learning data sets based on the feature vector extracted by the voice feature extraction unit and to recognize a speaker by assigning a weight depending on the selected reverberant environment to the speaker recognition score.

Abstract: Disclosed are a packet loss concealment method and apparatus a using a generative adversarial network. A method for packet loss concealment in voice communication may include training a classification model based on a generative adversarial network (GAN) with respect to a voice signal including a plurality of frames, training a generative model having a contention relation with the classification model based on the GAN, estimating lost packet information based on the trained generative model with respect to the voice signal encoded by a codec, and restoring a lost packet based on the estimated packet information.

Abstract: Provided is a speech enhancement method and a system therefor. The speech enhancement method includes receiving at least one speech signal; generating a first speech signal by performing a primary speech enhancement on the at least one speech signal; selecting a noise removing gain corresponding to the first speech signal from pre-learned noise removing gain information; and generating a second speech signal by performing a secondary speech enhancement on the first speech signal based on the selected noise removing gain.

Abstract: An apparatus for processing a speech signal is provided.

Abstract: Technologies are generally described for a method for measuring a quality of an audio signal in a mobile device. In some examples, the mobile device includes a receiving unit configured to receive an audio signal transmitted from another device; an audio quality measuring unit configured to measure a quality of the received audio signal; and a transmission unit configured to transmit the measured quality of the audio signal to the another device.

Abstract: A nonlinear acoustic echo signal suppression system and method using a Volterra filter is disclosed. The nonlinear acoustic echo signal suppression system includes an acoustic echo signal estimator configured to estimate a nonlinear acoustic echo signal by using a Volterra filter in a frequency filter, and a near-end talker speech signal generator configured to generate a near-end talker speech signal, in which the nonlinear acoustic echo signal is suppressed, by using a gain function based on a statistical model.

Abstract: An apparatus for processing a speech signal is provided.

Abstract: Technologies are generally described for a method for measuring a quality of an audio signal in a mobile device. In some examples, the mobile device includes a receiving unit configured to receive an audio signal transmitted from another device; an audio quality measuring unit configured to measure a quality of the received audio signal; and a transmission unit configured to transmit the measured quality of the audio signal to the another device.

Abstract: Technologies are generally described for a method for measuring a quality of an audio signal in a mobile device. In some examples, the mobile device includes a receiving unit configured to receive an audio signal transmitted from another device; an audio quality measuring unit configured to measure a quality of the received audio signal; and a transmission unit configured to transmit the measured quality of the audio signal to the another device.

Abstract: A nonlinear acoustic echo signal suppression system and method using a Volterra filter is disclosed. The nonlinear acoustic echo signal suppression system includes an acoustic echo signal estimator configured to estimate a nonlinear acoustic echo signal by using a Volterra filter in a frequency filter, and a near-end talker speech signal generator configured to generate a near-end talker speech signal, in which the nonlinear acoustic echo signal is suppressed, by using a gain function based on a statistical model.

Abstract: Technologies are generally described for a method for measuring a quality of an audio signal in a mobile device. In some examples, the mobile device includes a receiving unit configured to receive an audio signal transmitted from another device; an audio quality measuring unit configured to measure a quality of the received audio signal; and a transmission unit configured to transmit the measured quality of the audio signal to the another device.

Abstract: Disclosed herein is a method for emotion recognition based on a minimum classification error. In the method, a speaker's neutral emotion is extracted using a Gaussian mixture model (GMM), other emotions except the neutral emotion are classified using the Gaussian Mixture Model to which a discriminative weight for minimizing the loss function of a classification error for the feature vector for emotion recognition is applied. In the emotion recognition, the emotion recognition is performed by applying a discriminative weight evaluated using the Gaussian Mixture Model based on minimum classification error to feature vectors of the emotion classified with difficult, thereby enhancing the performance of emotion recognition.

Abstract: Disclosed herein is a method for emotion recognition based on a minimum classification error. In the method, a speaker's neutral emotion is extracted using a Gaussian mixture model (GMM), other emotions except the neutral emotion are classified using the Gaussian Mixture Model to which a discriminative weight for minimizing the loss function of a classification error for the feature vector for emotion recognition is applied. In the emotion recognition, the emotion recognition is performed by applying a discriminative weight evaluated using the Gaussian Mixture Model based on minimum classification error to feature vectors of the emotion classified with difficult, thereby enhancing the performance of emotion recognition.

Abstract: Disclosed is a voice activity detector using a complex Laplacian statistic module, the voice activity detector including: a fast Fourier transformer for performing a fast Fourier transform on input speech to analyze speech signals of a time domain in a frequency domain; a noise power estimator for estimating a power of noise signals from noisy speech of the frequency domain output from the fast Fourier transformer; and a likelihood ratio test (LRT) calculator for calculating a decision rule of voice activity detection (VAD) from the estimated power of noise signals from the noise power estimator and a complex Laplacian probabilistic statistical model.