I want to use a function SV Time-Varying Loudness in the Sound and vibration suite. The output of this function is exactly what I require for my speech analysis.
I have a speech sample recorded from the microphone obviously a voltage signal. This function requires a sound pressure signal.
The voltage signal would be proportional to the sound pressure signal right? How do I convert this voltage signal to the sound pressure signal (Pa).
I'm not even sure if I can use this function. I trying to extract the features from the speech signal. The algorithms used for this are linear predictive coding , perceptual linear predictive coding and mel frequency cepstral coefficients.
I already implemented Linear predictive coding in labVIEW. I wanted to try out Perceptual linear predictive coding because it is considered to be robust in noisy conditions.
This SV time varying loudness function does the exact thing I want to do but I don't know if it is applicable to speech signals.
In the help I says this VI process 2ms blocks of sound pressure data. But speech signals are to be processed only at 10 to 15ms. Please help
