.\" Copyright (c) 1987 Entropic Speech, Inc.; All rights reserved.\" @(#)fea_ana.5t	1.2 7/15/87 ESI.TH FEA_ANA 5\-ESPS 7/15/87.ds ]W "\fI\s+4\ze\h'0.05'e\s-4\v'-0.4m'\fP\(*p\v'0.4m'\ Entropic Speech, Inc..SH NAMEESPS ANA Feature File Subtype \- (.fana).SH SYNOPSIS.nf.ft B#include <sps/sps.h>#include <sps/fea.h>#include <sps/anafea.h>.fi.SH DESCRIPTION.PPThe FEA_ANA file is a subtype of the FEA file.  If \fIhd\fR is a pointer to the header of such a file, then \fIhd\->hd.fea\->fea_type\fR== FEA_ANA.  Such files are created by calling .I init_anafea_hd(3\-ESPSu) after .I new_header(3\-ESPSu).  .PPThe header for a FEA_ANAfile consists of the following generic header items:.PP.TScenter, box, tab(;);c | c | c | cl | l | l | l.Name;Size;Type;Enums=maxraw;1;long;maxlpc;1;long;maxpulses;1;long;order_vcd;1;long;order_unvcd;1;long;src_sf;1;float;filters;1;coded;NO,YESspec_rep;1;coded;\fIspec_reps\fPfilt_nsiz;1;short;filt_dsiz;1;short;.TE.PPThe generic header items have the following meanings:.IP maxrawMaximum number of raw powers per record..IP maxlpcMaximum number of lpc error powers per record..IP maxpulsesMaximum number of pitch pulses per record..IP order_vcdModel order (number of autoregressive coefficients) for voiced framesand transition frames..IP order_unvcdModel order (number of autoregressive coefficients) for unvoicedframes..IP src_sfSampling frequency of the header reference file \fIvariable.refer\fP.  .IP spec_repSpecifies the type of spectral parameters stored in the\fIspec_param\fP field of each record.  Values are defined in \fIanafea.h\fP with corresponding strings defined in the table\fIfspec_reps\fR in the FEA_ANA support module \fIanafeasupp.c\fP.  Currently supported values are RC, LAR, LSF, and AUTO.  .IP "filt_nsiz, filt_dsiz"The respective lengths of the numerator and denominator polynomials for the filters stored within each record; if \fIfilters\fP == YES, these are both zero and no space for filters is allocated in the records..PPThe header of a FEA_ANA file also contains definitions for the record fieldsas given by the following table:.PP.TScenter, box, tab(;);c | c | c | c | c | c l | l | l | l | l | l.Name;Size;Rank;Dimen;Type;Enums=frame_len;1;0;NULL;long;NULLnum_pulses;1;0;NULL;long;NULLframe_type;1;0;NULL;coded;\fIframe_types\fPvoiced_fraction;1;0;NULL;float;NULLraw_power;\fImaxraw\fP;1;NULL;float;NULLlpc_power;\fImaxlpc\fP;1;NULL;float;NULLp_pulse_len;\fImaxpulses\fP;1;NULL;float;NULLspec_param;MAX(\fIorder_vcd, order_unvcd\fP);1;NULL;float;NULLfilt_zeros;\fIfilt_nsiz\fP;1;NULL;float;NULLfilt_poles;\fIfilt_dsiz\fP;1;NULL;float;NULL.TE.PPIn the above table, \fIframe_types\fR is an array of of the possiblevalues the field \fIframe_type\fP can take.  These are defined in theFEA_ANA library support module \fIanafeasupp.c\fP.  See \fIfea\fR(5\-ESPS) for additional information on the meaning of the table columns..PPIn most cases, programs that deal with FEA_ANA files will use the supportroutines provided in the ESPS library and will not have to make directuse of the information in the above tables.   The library routine.I init_anafea_hd(3\-ESPSu) creates the record fields and the generic header items..PPPrograms that deal with FEA_ANA files do so in terms of structures oftype (struct anafea) \- pointers to structures of this type are returned by .I allo_anafea_rec(3\-ESPSu), and the FEA_ANA read and write routines (\fIget_anafea_rec\fRand \fIput_anafea_rec\fP) have parameters of type (struct anafea).  Here is the definition of the anafea struct (given in \fI<sps/anafea.h>\fR):.nf.ta .5i 1i 1.75i    struct anafea  {        long		*tag;	        long		*frame_len;        long		*num_pulses;        short		*frame_type;        float		*voiced_fraction;        float		*raw_power;	        float		*lpc_power;	        float		*p_pulse_len;	        float		*spec_param;        float		*filt_zeros;        float		*filt_poles;	        struct	    fea_data    *fea_rec;    };.fi.PPThe record fields have the following meanings:.IP tagposition tag in reference file \fIvariable.refer\fP, valid onlyif \fIcommon.tag\fP == YES.  This field is not represented in the table above, since it arises from general supportof ESPS files (see ESPS(5\-ESPS).  .IP frame_lennumber of samples represented by the frame.IP num_pulsesnumber of pitch pulses in frame \- only this number of \fIp_pulse_len[]\fP values are meaningful..IP frame_typeclassification of frame; numerical values are defined in\fIanafea.h\fP with corresponding strings defined in\fIanafeasupp.c\fP.  Common supported values are VOICED, UNVOICED,SILENCE, TRANSITION.  .IP voiced_fractionFraction of excitation energy that is voiced \- not all programssupport this field.  .IP "raw_power, lpc_power"These are respectively the raw and lpc error powers.  Starting with\fIraw_power[0]\fR, \fIraw_power\fR values are valid only until the first negativevalue, and starting with \fIlpc_power[0]\fR, \fIlpc_power\fR values are valid onlyuntil the first negative value, unless all are valid in which casenone of them are negative.  Typically, for a voiced frame thereshould be either one \fIraw_power\fR value (for the whole frame) or one foreach pulse.  For an unvoiced frame, typically there should be one \fIraw_power\fR value for the frame.  The situation for \fIlpc_power\fR is similar, except that one might have only one \fIlpc_power\fR for the frame even if there are \fIraw_power\fR values for every pitch pulse, and one might not have any \fIlpc_power\fR values at all.  .IP p_pulse_lenThese are the pitch pulse lengths; only the first \fInum_pulses\fP are significant, starting with \fIp_pulse_len[0]\fP.  .IP spec_paramThe spectral parameters, whose representation is determined by the generic header item \fIspec_rep\fP.  For VOICED or TRANSITION frames, \fIorder_vcd\fP values aremeaningful.  Otherwise, \fIorder_unvcd\fP values are meaningful.  If \fIspec_rep\fP == AUTO, the values stored in \fIspec_param\fP are the normalized autocorrelations R(i)/R(0), where R(i) is the autocorrelation function with sample delay i.  .IP "filt_zeros, filt_poles"Respectively the numerator and denominator polynomials of a record-specificfilter; the respective lengths are \fIfilt_nsiz\fP and \fIfilt_dsiz\fP.  Space for these polynomials is allocated only if the generic headeritem \fIfilters\fP is YES; otherwise these pointers are set to NULL..IP fea_recThis is a pointer to the FEA file record in which all the FEA_ANA information is stored.  Programs should not use this value directly..PPThe sign convention for spectral parameters is such that the firstreflection coefficient is R(1)/R(0) where R(1) and R(0) are autocorrelationfunctions with sample delays of 1 and 0 respectively..SH SEE ALSO.PPinit_anafea_hd(3\-ESPSu), allo_anafea_rec(3\-ESPSu), get_anafea_rec(3\-ESPSu),put_anafea_rec(3\-ESPSu), get_genhd(3\-ESPSu), ana2fea(1\-ESPS), fea2ana(1\-ESPS)FEA(5\-ESPS), ESPS(5\-ESPS).SH RECORD ELEMENT FILE STRUCTURE.PPIn order to use this (or any other) FEA file type with a generic ESPSprogram (one that operates on any file type) it is necessary to know theway that record elements are positioned in the file.   For a FEA filethat information is obtained by running the program\fIfea_element\fR(1\-ESPS) on the file in question..SH FILES.PP.nf/usr/include/sps/fea.h/usr/include/sps/anafea.h.SH AUTHORManual page by John Shore