13.17.2 Use

HSMOOTH is invoked via the command line

   HSmooth [options] hmmList accFile ...

where hmmList contains the list of context dependent models to be smoothed and each accFile is a file of the form HERN.acc dumped by a previous execution of HEREST with the -p option set to N. The HMM definitions are loaded and then for every state and stream of every context dependent model X, the optimal interpolation weight is found for smoothing between the mixture weights determined from the X accumulators alone and those determined from the context independent version of X. The latter is computed simply by summing the accumulators across all context dependent allophones of X.

The detailed operation of HSMOOTH is controlled by the following command line options

-b f
Set the value of epsilon for convergence in the binary chop optimisation procedure to f. The binary chop optimisation procedure for each interpolation weight terminates when the gradient is within epsilon of zero (default 0.001).

-c N
Set maximum number of interpolation iterations for the binary chop optimisation procedure to be N (default 16).

-d dir
Normally HSMOOTH expects to find the HMM definitions in the current directory. This option tells HSMOOTH to look in the directory dir to find them.

-m N
Set the minimum number of training examples required for any model to N. If the actual number falls below this value, the HMM is not updated and the original parameters are used for the new version (default value 1).

-o ext
This causes the file name extensions of the original models (if any) to be replaced by ext.

-s file
This causes statistics on occupation of each state to be output to the named file.

-u flags
By default, HSMOOTH updates all of the HMM parameters, that is, means, variances and transition probabilies. This option causes just the parameters indicated by the flags argument to be updated, this argument is a string containing one or more of the letters m (mean), v (variance) , t (transition) and w (mixture weight). The presence of a letter enables the updating of the corresponding parameter set.

-v f
This sets the minimum variance (i.e. diagonal element of the covariance matrix) to the real value f (default value 0.0).

-w f
Any mixture weight which falls below the global constant MINMIX is treated as being zero. When this parameter is set, all mixture weights are floored to f * MINMIX.

-x ext
By default, HSMOOTH expects a HMM definition for the model X to be stored in a file called X. This option causes HSMOOTH to look for the HMM definition in the file X.ext.

-B
Output HMM definition files in binary format.
-H mmf
Load HMM macro model file mmf. This option may be repeated to load multiple MMFs.
-M dir
Store output HMM macro model files in the directory dir. If this option is not given, the new HMM definition will overwrite the existing one.

HSMOOTH also supports the standard options -A, -C, -D, -S, -T, and -V as described in section 4.4.