next up previous contents index
Next: 5.7 Storage of Parameter Files Up: 5 Speech Input/Output Previous: 5.5 Energy Measures

5.6 Delta and Acceleration Coefficients

 

  The performance of a speech recognition system can be greatly enhanced by adding time derivatives to the basic static parameters. In HTK, these are indicated by attaching qualifiers to the basic parameter kind. The qualifier _D indicates that first order regression coefficients (referred to as delta coefficients) are appended, and the qualifier _A  indicates that second order regression coefficients (referred to as acceleration coefficients) are appended. The _A qualifier cannot be used without also using the _D  qualifier.

The delta coefficients  are computed using the following regression formula 

  equation4885

where tex2html_wrap_inline19924 is a delta coefficient at time t computed in terms of the corresponding static coefficients tex2html_wrap_inline19928 to tex2html_wrap_inline19930 . The value of tex2html_wrap_inline19932 is set using the configuration parameter DELTAWINDOW . The same formula is applied to the delta coefficients to obtain acceleration coefficients except that in this case the window size is set by ACCWINDOW . Since equation 5.16 relies on past and future speech parameter values, it some modification is needed at the beginning and end of the speech. The default behaviour is to replicate the first or last vector as needed to fill the regression window.

In older version 1.5 of HTK and earlier, this end-effect problem was solved by using simple first order differences at the start and end of the speech, that is

equation3768

and

equation3771

where T is the length of the data file. If required, this older behaviour can be restored by setting the configuration variable V1COMPAT  to true in HPARM.

For some purposes, it is useful to use simple differences throughout. This can be achieved by setting the configuration variable SIMPLEDIFFS  to true in HPARM. In this case, just the end-points of the delta window are used, i.e.

  equation4897

 

When delta and acceleration coefficients are requested, they are computed for all static parameters including energy if present. In some applications, the absolute energy is not useful but time derivatives of the energy may be. By including the _E qualifier together with the _N  qualifier, the absolute energy is suppressed leaving just the delta and acceleration coefficients of the energy.


next up previous contents index
Next: 5.7 Storage of Parameter Files Up: 5 Speech Input/Output Previous: 5.5 Energy Measures

ECRL HTK_V2.1: email [email protected]