view libgsmefr/enc_main.c @ 242:f081a6850fb5

libgsmfrp: new refined implementation The previous implementation exhibited the following defects, which are now fixed: 1) The last received valid SID was cached forever for the purpose of handling future invalid SIDs - we could have received some valid SID ages ago, then lots of speech or NO_DATA, and if we then get an invalid SID, we would resurrect the last valid SID from ancient history - a bad design. In our new design, we handle invalid SID based on the current state, much like BFI. 2) GSM 06.11 spec says clearly that after the second lost SID (received BFI=1 && TAF=1 in CN state) we need to gradually decrease the output level, rather than jump directly to emitting silence frames - we previously failed to implement such logic. 3) Per GSM 06.12 section 5.2, Xmaxc should be the same in all 4 subframes in a SID frame. What should we do if we receive an otherwise valid SID frame with different Xmaxc? Our previous approach would replicate this Xmaxc oddity in every subsequent generated CN frame, which is rather bad. In our new design, the very first CN frame (which can be seen as a transformation of the SID frame itself) retains the original 4 distinct Xmaxc, but all subsequent CN frames are based on the Xmaxc from the last subframe of the most recent SID.
author Mychaela Falconia <falcon@freecalypso.org>
date Tue, 09 May 2023 05:16:31 +0000
parents 035424a6ca83
children
line wrap: on
line source

/*
 * This module contains our GSM EFR encoder main function, EFR_encode_params(),
 * that stands at the boundary between our public interface and the guts of
 * ETSI-based codec.
 */

#include "gsm_efr.h"
#include "typedef.h"
#include "namespace.h"
#include "basic_op.h"
#include "cnst.h"
#include "codec.h"
#include "sig_proc.h"
#include "memops.h"
#include "enc_state.h"
#include "e_homing.h"
#include "dtx.h"

void EFR_encode_params(struct EFR_encoder_state *st, const int16_t *pcm_in,
			int16_t *params, int *sp_out, int *vad_out)
{
	Word16 *new_speech = st->old_speech + L_TOTAL - L_FRAME;
	Word16 syn[L_FRAME];
	Word16 reset_flag;
	Word16 i;

        /* Check whether this frame is an encoder homing frame */
        reset_flag = encoder_homing_frame_test (pcm_in);

        for (i = 0; i < L_FRAME; i++)   /* Delete the 3 LSBs (13-bit input) */
        {
            new_speech[i] = pcm_in[i] & 0xfff8;
        }

        Pre_Process (st, new_speech, L_FRAME);       /* filter + downscaling */

        Coder_12k2 (st, params, syn);    /* Find speech parameters   */

        if ((st->txdtx_ctrl & TX_SP_FLAG) == 0)
        {
            /* Write comfort noise parameters into the parameter frame.
            Use old parameters in case SID frame is not to be updated */
            CN_encoding (st, params, st->txdtx_ctrl);
        }

        /* VAD and SP flag outputs */
        if (vad_out)
            *vad_out = ((st->txdtx_ctrl & TX_VAD_FLAG) != 0);

        if (sp_out)
            *sp_out = ((st->txdtx_ctrl & TX_SP_FLAG) != 0);

        if (reset_flag != 0)
        {
            /* Bring the encoder, VAD and DTX to the home state */
            EFR_encoder_reset(st, st->dtx_mode);
        }
}