Method and system using successive differences of speech signals for emotion identification

A system of speech signal processing, comprising:

• a memory module storing a plurality of instructions;
• one or more communication interfaces;
• and
• one or more hardware processors coupled to the memory module via the one or more communication interfaces, wherein the one or more hardware processors are caused by the plurality of instructions to:
• collect a speech signal from at least one user, as input;
• extract a plurality of differential features from the speech signal to generate a feature file, by:
• sampling the speech signal at a defined sampling rate to generate a plurality of sampled speech signals;
• splitting each of the plurality of sampled speech signals to a plurality of overlapping or non-overlapping frames of 20 milliseconds length;
• iteratively performing for each of the plurality of frames, for a pre-defined number of times:
• selecting one sample in every M samples of the speech signal in the frame, where M is 2;
• and
• calculating differences between adjacent samples of the frame as the differential feature to get an output frame of size (L−(N)), where L is number of samples in a frame divided by M, and N represents number of times the difference between adjacent values is calculated;
• extract the plurality of features from the plurality of differential features of the plurality of overlapping or non-overlapping frames;
• compare each of the differential features with an emotion recognition model to identify at least one emotion corresponding to the speech signal;
• and
• associate the identified at least one emotion with the speech signal.

A method for signal processing, comprising:

• generating a plurality of differential features corresponding to a signal by iteratively performing for each a plurality of frames of the signal, for a pre-defined number of times:
• selecting one sample in every M samples of the speech signal in the frame;
• and
• calculating differences between adjacent samples of the frame as the differential feature to get an output frame of size (L−(N)), where L is number of samples in a frame divided by M, and N represents number of times the difference between adjacent values is calculated.

A non-transitory computer readable medium for speech signal processing, the non-transitory computer readable medium performs the speech signal processing by:

• collecting a speech signal from at least one user, as input, via one or more hardware processors;
• extracting a plurality of differential features from the speech signal to generate a feature file, via the one or more hardware processors, by:
• sampling the speech signal at a defined sampling rate to generate a plurality of sampled speech signals;
• splitting each of the plurality of sampled speech signals to a plurality of overlapping or non-overlapping frames of 20 milliseconds length;
• iteratively performing for each of the plurality of frames, for a pre-defined number of times:
• selecting one sample in every M samples of the speech signal in the frame, where M is 2;
• and
• calculating differences between adjacent samples of the frame as the differential feature to get an output frame of size (L−(N)), where L is number of samples in a frame divided by M, and N represents number of times the difference between adjacent values is calculated;
• extracting the plurality of features from the plurality of differential features of the plurality of overlapping or non-overlapping frames, via the one or more hardware processors;
• comparing each of the differential features with an emotion recognition model to identify at least one emotion corresponding to the speech signal, via the one or more hardware processors;
• and
• associating the identified at least one emotion with the speech signal, via the one or more hardware processors.

A non-transitory computer readable medium for signal processing, the non-transitory computer readable medium performs the speech signal processing by:

• generating a plurality of differential features corresponding to a signal by iteratively performing for each a plurality of frames of the signal, for a pre-defined number of times:
• selecting one sample in every M samples of the speech signal in the frame;
• and
• calculating differences between adjacent samples of the frame as the differential feature to get an output frame of size (L−(N)), where L is number of samples in a frame divided by M, and N represents number of times the difference between adjacent values is calculated.