Abstract: A speech processing method, performed by an electronic device, includes determining a first speech feature and a first text bottleneck feature based on to-be-processed speech information, determining a first combined feature vector based on the first speech feature and the first text bottleneck feature, inputting the first combined feature vector to a trained unidirectional long short-term memory (LSTM) model, performing speech processing on the first combined feature vector to obtain speech information after noise reduction, and transmitting the obtained speech information after noise reduction to another electronic device for playing.

Abstract: An acute kidney injury predicting system and a method thereof are proposed. A processor reads the data to be tested, the detection data, the machine learning algorithm and the risk probability comparison table from a main memory. The processor trains the detection data according to the machine learning algorithm to generate an acute kidney injury prediction model, and inputs the data to be tested into the acute kidney injury prediction model to generate an acute kidney injury characteristic risk probability and a data sequence table. The data sequence table lists the data to be tested in sequence according to a proportion of each of the data to be tested in the acute kidney injury characteristics. The processor selects one of the medical treatment data from the risk probability comparison table according to the acute kidney injury characteristic risk probability.

Abstract: A speech signal dereverberation processing method includes extracting an amplitude spectrum feature and a phase spectrum feature of a current frame in an original speech signal, extracting subband amplitude spectrums from the amplitude spectrum feature corresponding to the current frame, determining, based on the subband amplitude spectrums and by using a first reverberation predictor, a reverberation strength indicator corresponding to the current frame, and determining, based on the subband amplitude spectrums and the reverberation strength indicator, and by using a second reverberation predictor, a clean speech subband spectrum corresponding to the current frame.

Abstract: A speech processing method, performed by an electronic device, includes determining a first speech feature and a first text bottleneck feature based on to-be-processed speech information, determining a first combined feature vector based on the first speech feature and the first text bottleneck feature, inputting the first combined feature vector to a trained unidirectional long short-term memory (LSTM) model, performing speech processing on the first combined feature vector to obtain speech information after noise reduction, and transmitting the obtained speech information after noise reduction to another electronic device for playing.