Abstract: A heart rate detection method includes: acquiring a plurality of time-domain heart rate detection data; if the time-domain heart rate detection data includes a weak interference signal, extracting a first feature point from the time-domain heart rate detection data, and collecting statistics on feature data of the first feature point to determine time-domain heart rate detection data used in calculating heart rate; if the time-domain heart rate detection data includes a strong interference signal, transforming the time-domain heart rate detection data to a frequency domain to obtain a plurality of frequency-domain heart rate detection data, extracting a second feature point from the frequency-domain heart rate detection data, and collecting statistics on feature data of the second feature point to determine frequency-domain heart rate detection data used in calculating heart rate; and calculating the heart rate based on the time-domain or the frequency-domain heart rate detection data.

Abstract: The present disclosure provides a speech enhancement method and apparatus, a device and a storage medium. The method includes: acquiring a first speech signal and a second speech signal; obtaining a signal to noise ratio of the first speech signal; determining, according to the signal to noise ratio of the first speech signal, a fusion coefficient of filtered signals corresponding to the first speech signal and the second speech signal; and performing, according to the fusion coefficient, speech fusion processing on the filtered signals corresponding to the first speech signal and the second speech signal to obtain an enhanced speech signal. Thereby, it is realized that a fusion coefficient of speech signals of a non-air conduction speech sensor and an air conduction speech sensor is adaptively adjusted according to environment noise, thereby improving the signal quality after speech fusion, and improving the effect of speech enhancement.

Abstract: A method for eliminating motion interference includes: performing dimensionality reduction on the multi-dimensional acceleration signal to obtain a one-dimensional acceleration signal that represents motion interference; mixing the first signal and the second signal through a plurality of preset coefficients ri respectively, so as to calculate a plurality of mixed signals corresponding to the plurality of preset coefficients; calculating a correlation coefficient between each of the mixed signals and the one-dimensional acceleration signal; obtaining a preset coefficient corresponding to the maximum correlation coefficient among the correlation coefficients and a preset coefficient corresponding to the minimum correlation coefficient among the correlation coefficients; and calculating a signal with motion interference being eliminated from the measurement signal to be processed, according to the first signal, the second signal, the preset coefficient corresponding to the maximum correlation coefficient, and t

Abstract: The present disclosure provides a speech enhancement method and apparatus, a device and a storage medium. The method includes: acquiring a first speech signal and a second speech signal; obtaining a signal to noise ratio of the first speech signal; determining, according to the signal to noise ratio of the first speech signal, a fusion coefficient of filtered signals corresponding to the first speech signal and the second speech signal; and performing, according to the fusion coefficient, speech fusion processing on the filtered signals corresponding to the first speech signal and the second speech signal to obtain an enhanced speech signal. Thereby, it is realized that a fusion coefficient of speech signals of a non-air conduction speech sensor and an air conduction speech sensor is adaptively adjusted according to environment noise, thereby improving the signal quality after speech fusion, and improving the effect of speech enhancement.

Abstract: A heart rate detection method includes: acquiring a plurality of time-domain heart rate detection data; if the time-domain heart rate detection data includes a weak interference signal, extracting a first feature point from the time-domain heart rate detection data, and collecting statistics on feature data of the first feature point to determine time-domain heart rate detection data used in calculating heart rate; if the time-domain heart rate detection data includes a strong interference signal, transforming the time-domain heart rate detection data to a frequency domain to obtain a plurality of frequency-domain heart rate detection data, extracting a second feature point from the frequency-domain heart rate detection data, and collecting statistics on feature data of the second feature point to determine frequency-domain heart rate detection data used in calculating heart rate; and calculating the heart rate based on the time-domain or the frequency-domain heart rate detection data.

Abstract: A method for eliminating motion interference includes: performing dimensionality reduction on the multi-dimensional acceleration signal to obtain a one-dimensional acceleration signal that represents motion interference; mixing the first signal and the second signal through a plurality of preset coefficients ri respectively, so as to calculate a plurality of mixed signals corresponding to the plurality of preset coefficients; calculating a correlation coefficient between each of the mixed signals and the one-dimensional acceleration signal; obtaining a preset coefficient corresponding to the maximum correlation coefficient among the correlation coefficients and a preset coefficient corresponding to the minimum correlation coefficient among the correlation coefficients; and calculating a signal with motion interference being eliminated from the measurement signal to be processed, according to the first signal, the second signal, the preset coefficient corresponding to the maximum correlation coefficient, and t