A method, computer program, and computer system is provided for an all-deep-learning based AEC system by recurrent neural networks. The model consists of two stages, echo estimation stage and echo suppression stage, respectively. Two different schemes for echo estimation are presented herein: linear echo estimation by multi-tap filtering on far-end reference signal and non-linear echo estimation by single-tap masking on microphone signal. A microphone signal waveform and a far-end reference signal waveform are received. An echo signal waveform is estimated based on the microphone signal waveform and a far-end reference signal waveform. A near-end speech signal waveform is output based on subtracting the estimated echo signal waveform from the microphone signal waveform, and echoes are suppressed within the near-end speech signal waveform.

[Problem] To provide a communication apparatus that makes a subject's voice more audible. [Means for Solution] A communication apparatus 60 has: a microphone 61 for receiving, during rotation of a rotating section 26, sound containing a voice of a subject 5 to be examined and noise caused by the rotation of the rotating section 26; a DSP 623 for executing filter processing for reducing said noise contained in the sound received by the microphone 61, wherein the DSP 623 determines a frequency of the noise caused by the rotation of the rotating section 26 based on a rotational speed vi of the rotating section 26, and sets a filter characteristic F(ti) for the DSP so that a frequency component of the noise contained in the sound is removed; and a speaker 63 for outputting the sound which contains the voice of the subject 5 and from which the frequency component of said noise has been removed.

A method, a system and a program product for evaluating an intestinal function using bowel sounds are disclosed. The method comprises the following steps: A. continuously monitoring an abdominal cavity of an examinee within a specific time by using an audio collection apparatus, collecting a bowel sound signal of an intestinal tract inside the abdominal cavity, and converting the bowel sound signal into a digital signal; B. using higher-order statistics (HOS), by a processing unit, to remove noise from the digital signal; C. using a fractal dimension algorithm, by the processing unit, to capture a high-complexity feature from the digital signal, and defining the high-complexity feature as an intestinal motility signal, and D. evaluating the intestinal function of the examinee, by the processing unit, according to the intestinal motility signal.

The present disclosure relates to a video processing method for an application and an electronic device. The method comprises: receiving a configuration instruction for an audio during an editing process of a video; and configuring the audio during a shooting process of the video in response to the configuration instruction, and displaying a microphone control in a shooting page of the video in a case where a configuration result indicates that the audio is configured during the shooting process of the video; wherein recording of an original sound is configured during the shooting process of the video when the microphone control is in an on state, and not recording of the original sound is configured during the shooting process of the video when the microphone control is in an off state.

An audio feedback detection apparatus including: a first audio signal input unit configured to acquire a first audio signal collected by a microphone; a second audio signal input unit configured to acquire a second audio signal from an audio communication application to be output to a speaker; and an audio feedback determination unit configured to determine whether an audio feedback is present based on a correlation between a frequency characteristic of the first audio signal input to the audio communication application and a frequency characteristic of the second audio signal input to the speaker. One of the microphone and the speaker is located on a path in which the audio feedback occurs, and the other of the microphone and the speaker is located on a path in which the audio feedback does not occur.

A computer implemented method, system and computer program product are provided that implement a neural network (NN) audio filter. The method, system and computer program product obtain an electronic audio signal comprising a speech impaired message and apply the audio signal to the NN audio filter to modify the speech impaired message to form an unimpaired message. The method, system and computer program product output the unimpaired message.

The present invention relates to a method for receiving data transmitted acoustically. The method includes receiving an acoustically transmitted signal encoding data; processing the received signal to minimise environmental interference within the received signal: and decoding the processed signal to extract the data. The data encoded within the signal using a sequence of tones. A method for encoding data for acoustic transmission is also disclosed. This method includes encoding data into an audio signal using a sequence of tones. The audio signal in this method is configured to minimise environmental interference. A system and software are also disclosed.

Selecting audio noise reduction models for noise suppression in an information handling system (IHS), including performing calibration and configuration of an audio noise reduction selection model, including: identifying contextual data associated with contextual inputs to the IHS; training, based on the contextual data, the audio noise reduction selection model, including generating a configuration policy including configuration rules, the configuration rules for performing actions for selection of a combination of audio noise reduction models to reduce combinations of noise sources associated with the IHS; performing steady-state monitoring of the IHS, including: monitoring the contextual inputs of the IHS, and in response, accessing the audio noise reduction selection model, identifying configuration rules based on the monitored contextual inputs, applying the configuration rules to select a particular combination of audio noise reduction models, applying particular combination of audio noise reduction models to reduce a particular combination of noise sources associated with the IHS.

According to an aspect, a WPE-based dereverberation apparatus using virtual acoustic channel expansion based on a deep neural network includes a signal reception unit for receiving as input a first speech signal through a single channel microphone, a signal generation unit for generating a second speech signal by applying a virtual acoustic channel expansion algorithm based on a deep neural network to the first speech signal and a dereverberation unit for removing reverberation of the first speech signal and generating a dereverberated signal from which the reverberation has been removed by applying a dual-channel weighted prediction error (WPE) algorithm based on a deep neural network to the first speech signal and the second speech signal.

A noise cancellation filter structure for a noise cancellation enabled audio device, in particular headphone, comprises a noise input for receiving a noise signal and a filter output for providing a filter output signal. A first noise filter produces a first filter signal by filtering the noise signal and a second noise filter produces a second filter signal by filtering the noise signal. The second noise filter has a frequency response with a non-minimum-phase, in particular maximum-phase. A combiner is configured to provide the filter output signal based on a linear combination of the first filter signal and the second filter signal.