view libtwamr/cod_amr.h @ 581:e2d5cad04cbf

libgsmhr1 RxFE: store CN R0+LPC separately from speech In the original GSM 06.06 code the ECU for speech mode is entirely separate from the CN generator, maintaining separate state. (The main intertie between them is the speech vs CN state variable, distinguishing between speech and CN BFIs, in addition to the CN-specific function of distinguishing between initial and update SIDs.) In the present RxFE implementation I initially thought that we could use the same saved_frame buffer for both ECU and CN, overwriting just the first 4 params (R0 and LPC) when a valid SID comes in. However, I now realize it was a bad idea: the original code has a corner case (long sequence of speech-mode BFIs to put the ECU in state 6, then SID and CN-mode BFIs, then a good speech frame) that would be broken by that buffer reuse approach. We could eliminate this corner case by resetting the ECU state when passing through a CN insertion period, but doing so would needlessly increase the behavioral diffs between GSM 06.06 and our version. Solution: use a separate CN-specific buffer for CN R0+LPC parameters, and match the behavior of GSM 06.06 code in this regard.
author Mychaela Falconia <falcon@freecalypso.org>
date Thu, 13 Feb 2025 10:02:45 +0000
parents 93d6c6960a46
children
line wrap: on
line source

/*
*****************************************************************************
*
*      GSM AMR-NB speech codec   R98   Version 7.6.0   December 12, 2001
*                                R99   Version 3.3.0                
*                                REL-4 Version 4.1.0                
*
*****************************************************************************
*
*      File             : cod_amr.h
*      Purpose          : Main encoder routine operating on a frame basis.
*
*****************************************************************************
*/
#ifndef cod_amr_h
#define cod_amr_h "$Id $"

/*
*****************************************************************************
*                         INCLUDE FILES
*****************************************************************************
*/
#include "tw_amr.h"
#include "typedef.h"
#include "cnst.h"
#include "lpc.h"
#include "lsp.h"
#include "cl_ltp.h"
#include "gain_q.h"
#include "p_ol_wgh.h"
#include "ton_stab.h"
#include "vad.h"
#include "dtx_enc.h"
 
/*
*****************************************************************************
*                         DEFINITION OF DATA TYPES
*****************************************************************************
*/
/*-----------------------------------------------------------*
 *    Coder constant parameters (defined in "cnst.h")        *
 *-----------------------------------------------------------*
 *   L_WINDOW    : LPC analysis window size.                 *
 *   L_NEXT      : Samples of next frame needed for autocor. *
 *   L_FRAME     : Frame size.                               *
 *   L_FRAME_BY2 : Half the frame size.                      *
 *   L_SUBFR     : Sub-frame size.                           *
 *   M           : LPC order.                                *
 *   MP1         : LPC order+1                               *
 *   L_TOTAL7k4  : Total size of speech buffer.              *
 *   PIT_MIN7k4  : Minimum pitch lag.                        *
 *   PIT_MAX     : Maximum pitch lag.                        *
 *   L_INTERPOL  : Length of filter for interpolation        *
 *-----------------------------------------------------------*/
typedef struct {
   /* Speech vector */
   Word16 old_speech[L_TOTAL];
   Word16 *speech, *p_window, *p_window_12k2;
   Word16 *new_speech;             /* Global variable */
   
   /* Weight speech vector */
   Word16 old_wsp[L_FRAME + PIT_MAX];
   Word16 *wsp;

   /* OL LTP states */
   Word16 old_lags[5];
   Word16 ol_gain_flg[2];

   /* Excitation vector */
   Word16 old_exc[L_FRAME + PIT_MAX + L_INTERPOL];
   Word16 *exc;

   /* Zero vector */
   Word16 ai_zero[L_SUBFR + MP1];
   Word16 *zero;

   /* Impulse response vector */
   Word16 *h1;
   Word16 hvec[L_SUBFR * 2];

   /* Substates */
   lpcState   lpcSt;
   lspState   lspSt;
   clLtpState clLtpSt;
   gainQuantState  gainQuantSt;
   pitchOLWghtState pitchOLWghtSt;
   tonStabState tonStabSt;
   vadState vadSt;
   Flag dtx;
   dtx_encState dtx_encSt;

   /* Filter's memory */
   Word16 mem_syn[M], mem_w0[M], mem_w[M];
   Word16 mem_err[M + L_SUBFR], *error;

   Word16 sharp;
} cod_amrState;

/*
********************************************************************************
*                         DECLARATION OF PROTOTYPES
********************************************************************************
*/

/*
**************************************************************************
*
*  Function    : cod_amr_reset
*  Purpose     : Resets state memory
*  Returns     : 0 on success
*
**************************************************************************
*/
void cod_amr_reset (cod_amrState *st, Flag dtx, Flag use_vad2);

/***************************************************************************
 *   FUNCTION:   cod_amr_first
 *
 *   PURPOSE:  Copes with look-ahead.
 *
 *   INPUTS:
 *       No input argument are passed to this function. However, before
 *       calling this function, 40 new speech data should be copied to the
 *       vector new_speech[]. This is a global pointer which is declared in
 *       this file (it points to the end of speech buffer minus 200).
 *
 ***************************************************************************/
 
int cod_amr_first(cod_amrState *st,     /* i/o : State struct            */
                  Word16 new_speech[]   /* i   : speech input (L_FRAME)  */
);

/***************************************************************************
 *   FUNCTION:   cod_amr
 *
 *   PURPOSE:  Main encoder routine.
 *
 *   DESCRIPTION: This function is called every 20 ms speech frame,
 *       operating on the newly read 160 speech samples. It performs the
 *       principle encoding functions to produce the set of encoded parameters
 *       which include the LSP, adaptive codebook, and fixed codebook
 *       quantization indices (addresses and gains).
 *
 *   INPUTS:
 *       No input argument are passed to this function. However, before
 *       calling this function, 160 new speech data should be copied to the
 *       vector new_speech[]. This is a global pointer which is declared in
 *       this file (it points to the end of speech buffer minus 160).
 *
 *   OUTPUTS:
 *
 *       ana[]:     vector of analysis parameters.
 *       synth[]:   Local synthesis speech (for debugging purposes)
 *
 ***************************************************************************/

int cod_amr(cod_amrState *st,         /* i/o : State struct                 */
            enum Mode mode,           /* i   : AMR mode                     */
            Word16 new_speech[],      /* i   : speech input (L_FRAME)       */
            Word16 ana[],             /* o   : Analysis parameters          */
            enum Mode *usedMode,      /* o   : used mode                    */
            Word16 synth[]            /* o   : Local synthesis              */
);

#endif