Linear Prediction Coefficients for ASR

[Yichao L]

Hi,

I recall from previous modules that we used linear prediction analysis as a mean of performing the source-filter separation which is similar to cepstral analysis.

Therefore I wonder how those coefficients perform in ASR tasks compared to the MFCCs, and why?

Thanks,

Yichao

[Simon]

That’s a great question. If we read outdated books like Holmes & Holmes we will find discussion of LPC features for ASR, and other features derived from a source-filter analysis such as PLP (Perceptual Linear Prediction). PLP was popular for quite a while.

LPC analysis makes a strong assumption about the shape of the spectral envelope: that it can be modelled as an all-pole filter. MFCCs use a more general-purpose approach of series expansion that does not make this assumption.

LPC analysis requires solving for the filter co-efficients, and there are multiple ways to do that. They all have limitations, and the process can be error prone, especially when the speech is not clean.

[Author]

Posts