Feature extraction of acoustic signals

A computer system for selecting an acoustic feature extractor, the computer system having a processing unit and a memory coupled to the processing unit and storing instructions thereon, the instructions executed by the processing unit to perform a method comprising:

• acquiring a frame of an acoustic signal;
• checking a status of a flag for indicating an acoustic feature extractor to be selected;
• processing the frame of the acoustic signal by the acoustic feature extractor indicated by the checked status;
• determining, based on data generated in the processing of the frame of the acoustic signal, an actual status of the frame of the acoustic signal;
• and
• determining a new status of the flag based on the determined actual status,
• wherein the checked status of the flag and the determined new status of the flag includes a first status and a second status, wherein the first status indicates a Linear Predictive Cepstral Coefficients (LPC) based feature extractor associated with a stationary acoustic signal and the second status indicates a Mel-frequency Cepstral Coefficients (MFCC) based feature extractor associated with a non-stationary acoustic signal.

A computer program product used for selecting an acoustic feature extractor, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to:

• acquiring a frame of an acoustic signal;
• checking a status of a flag for indicating an acoustic feature extractor to be selected;
• processing the frame of the acoustic signal by the acoustic feature extractor indicated by the checked status;
• determining, based on data generated in the processing of the frame of the acoustic signal, an actual status of the frame of the acoustic signal;
• and
• determining a new status of the flag based on the determined actual status,
• wherein the checked status of the flag and the determined new status of the flag includes a first status and a second status, wherein the first status indicates a Linear Predictive Cepstral Coefficients (LPC) based feature extractor associated with a stationary acoustic signal and the second status indicates a Mel-frequency Cepstral Coefficients (MFCC) based feature extractor associated with a non-stationary acoustic signal.