The subject of the present patent is a method to determine the flame shape of a swirling flame in a steady-operating burner in a closed combustion chamber. The broadband combustion noise of the burner is sensed inside the combustion chamber, and the spectrum and the sound pressure levels are calculated from the acoustic vibrations of the process. The conclusions are made on this data to determine the flame shape. To determine the governing frequencies, the burner is investigated at various operating conditions. At least one parameter from the fuel flow rate, combustion air flow rate, and the swirl number is varied in the physically accessible range of the burner. The spectrum is divided into 0-500 Hz, 501-2000 Hz, and 2 kHz-6 kHz frequency ranges, then the amplitudes at the band center frequencies are calculated. Based on either the temporal analysis of band center frequencies or the temporal variation of their ratio or the two combined, the shape of the swirling flame can be determined.

In order to estimate the trajectory of a moving wave source, this trajectory estimation device (10) comprises: an acquisition unit (11) that acquires wave motion data based on wave motion detected by a plurality of sensors (100); a generation unit (12) that generates a spectrogram using the wave motion data; an extraction unit (13) that extracts a Doppler shift from the spectrogram; a selection unit (14) that selects, as a sensor pair, two sensors that satisfy a preset selection condition pertaining to the Doppler shift; and an estimation unit (15) that estimates the trajectory of a wave source, which is the source generating the wave motion, on the basis of the positional relationship between the sensors constituting the sensor pair and the relationship of the Doppler shift between the two sensors constituting the sensor pair.

Systems and methods for Evidence-based Sound Event Early Detection is provided. The system/method includes parsing collected labeled audio corpus data and real time audio streaming data utilizing mel-spectrogram, encoding features of the parsed mel-spectrograms using a trained neural network, and generating a final predicted result for a sound event based on the belief, disbelief and uncertainty outputs from the encoded mel-spectrograms.

Systems and methods for Evidence-based Sound Event Early Detection is provided. The system/method includes parsing collected labeled audio corpus data and real time audio streaming data utilizing mel-spectrogram, encoding features of the parsed mel-spectrograms using a trained neural network, and generating a final predicted result for a sound event based on the belief, disbelief and uncertainty outputs from the encoded mel-spectrograms.

Systems and methods for identifying potential bullying are disclosed. In various aspects, a system for identifying potential bullying includes a sound detector configured to provide samples of sounds over time, a processor, and a memory storing instructions. The instructions, when executed by the processor, cause the system to determine that a noise event has occurred by processing the samples to determine that the sounds exceed a sound level threshold over a time period that exceeds a time period threshold, process the samples to provide frequency spectrum information of the noise event, determine whether the noise event is a potential bullying occurrence based on comparing the frequency spectrum information of the noise event and at least one frequency spectrum profile, and initiate a bullying notification in a case of determining that the noise event is a potential bullying occurrence.

The present invention relates to a method for identifying a sound source comprising the following steps: (S1): acquisition of a sound signal; (S2): application of a frequency fitter to the acquired sound signal in order to obtain a filtered signal; (S4): extraction of a matrix of features associated with the filtered signal; (S5): identification of the source by applying a classification model to the feature matrix extracted in step (S4), the classification model having, as its output, at least one class associated with the source of the acquired sound signal.

A partial discharge determination method and apparatus, and a partial discharge determination system capable of indicating how much margin is left before dielectric breakdown, in a lighting impulse withstand voltage test, and a power device for which whether partial discharge is caused is determined by them, and a method for manufacturing a power device including the partial discharge determination method. A low-pass filter receives an acoustic signal resulting from application of an impulse voltage and acquired by an acoustic emission sensor, and removes an electromagnetic noise superimposed on the acoustic signal. A mechanical oscillation removal unit removes a mechanical oscillation component of a device under test, from the acoustic signal resulting from application of the impulse voltage which is a high voltage, based on the mechanical oscillation component acquired in advance and included in the acoustic signal resulting from application of the impulse voltage which is a low voltage.

A transient multi-tone test signal is generated to detect piano noise distortion played back by a speaker. The test signal has a number, such as three, formant tones resembling a piano chord and selectable such that the frequencies and harmonics remain distributed in frequency. The test signal provides a basis for defining normal speaker operating performance and allows a user to define speaker responses that fall outside of normal boundaries by highlighting piano noise distortion detected during speaker playback of the test signal.

A transient multi-tone test signal is generated to detect piano noise distortion played back by a speaker. The test signal has a number, such as three, formant tones resembling a piano chord and selectable such that the frequencies and harmonics remain distributed in frequency. The test signal provides a basis for defining normal speaker operating performance and allows a user to define speaker responses that fall outside of normal boundaries by highlighting piano noise distortion detected during speaker playback of the test signal.

A sound leakage suppression apparatus for suppressing sound produced in a room from leaking outside thereof, includes a microphone, a display, and a processor configured to acquire information indicating sound insulation property of the room, based on the acquired information, determine a maximum volume level of sound that is permitted for each of a plurality of predetermined frequencies, control the microphone to collect sound produced in the room at a first time and determine a current volume level of the sound produced at the first time separately for each of the predetermined frequencies, and control the display to display both the maximum volume level and the current volume level for each of the predetermined frequencies.