[FFmpeg-devel] [PATCH] g722 decoder, no licensing fame
Kenan Gillet
kenan.gillet
Thu Apr 9 17:14:58 CEST 2009
On Thu, Apr 9, 2009 at 12:12 AM, Diego Biurrun <diego at biurrun.de> wrote:
> On Wed, Apr 08, 2009 at 09:23:51PM -0700, Kenan Gillet wrote:
>>
>> here is a version 3 of the patch:
>> - it includes the Diego's suggested changes
>
> It does not.
darn, i double checked the changes, and just ended up attaching the
wrong file :(
anyway correct patch attached,
thanks Diego
Kenan
-------------- next part --------------
Index: Changelog
===================================================================
--- Changelog (revision 18382)
+++ Changelog (working copy)
@@ -8,6 +8,7 @@
- PCX encoder
- RTP packetization of H.263
- RTP packetization of AMR
+- G.722 ADPCM audio encoder/decoder
Index: doc/general.texi
===================================================================
--- doc/general.texi (revision 18382)
+++ doc/general.texi (working copy)
@@ -482,6 +483,7 @@
@item ADPCM Electronic Arts R2 @tab @tab X
@item ADPCM Electronic Arts R3 @tab @tab X
@item ADPCM Electronic Arts XAS @tab @tab X
+ at item ADPCM G.722 @tab X @tab X
@item ADPCM G.726 @tab X @tab X
@item ADPCM IMA AMV @tab @tab X
@tab Used in AMV files
Index: libavcodec/avcodec.h
===================================================================
--- libavcodec/avcodec.h (revision 18382)
+++ libavcodec/avcodec.h (working copy)
@@ -30,7 +30,7 @@
#include "libavutil/avutil.h"
#define LIBAVCODEC_VERSION_MAJOR 52
-#define LIBAVCODEC_VERSION_MINOR 25
+#define LIBAVCODEC_VERSION_MINOR 26
#define LIBAVCODEC_VERSION_MICRO 0
#define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \
@@ -249,6 +249,7 @@
CODEC_ID_ADPCM_EA_XAS,
CODEC_ID_ADPCM_EA_MAXIS_XA,
CODEC_ID_ADPCM_IMA_ISS,
+ CODEC_ID_ADPCM_G722,
/* AMR */
CODEC_ID_AMR_NB= 0x12000,
Index: libavcodec/allcodecs.c
===================================================================
--- libavcodec/allcodecs.c (revision 18382)
+++ libavcodec/allcodecs.c (working copy)
@@ -272,6 +272,7 @@
REGISTER_DECODER (ADPCM_EA_R2, adpcm_ea_r2);
REGISTER_DECODER (ADPCM_EA_R3, adpcm_ea_r3);
REGISTER_DECODER (ADPCM_EA_XAS, adpcm_ea_xas);
+ REGISTER_ENCDEC (ADPCM_G722, adpcm_g722);
REGISTER_ENCDEC (ADPCM_G726, adpcm_g726);
REGISTER_DECODER (ADPCM_IMA_AMV, adpcm_ima_amv);
REGISTER_DECODER (ADPCM_IMA_DK3, adpcm_ima_dk3);
Index: libavcodec/Makefile
===================================================================
--- libavcodec/Makefile (revision 18382)
+++ libavcodec/Makefile (working copy)
@@ -329,6 +329,8 @@
OBJS-$(CONFIG_ADPCM_EA_R2_DECODER) += adpcm.o
OBJS-$(CONFIG_ADPCM_EA_R3_DECODER) += adpcm.o
OBJS-$(CONFIG_ADPCM_EA_XAS_DECODER) += adpcm.o
+OBJS-$(CONFIG_ADPCM_G722_DECODER) += g722.o
+OBJS-$(CONFIG_ADPCM_G722_ENCODER) += g722.o
OBJS-$(CONFIG_ADPCM_G726_DECODER) += g726.o
OBJS-$(CONFIG_ADPCM_G726_ENCODER) += g726.o
OBJS-$(CONFIG_ADPCM_IMA_AMV_DECODER) += adpcm.o
Index: libavcodec/g722.c
===================================================================
--- libavcodec/g722.c (revision 0)
+++ libavcodec/g722.c (revision 0)
@@ -0,0 +1,350 @@
+/*
+ * G.722 ADPCM audio decoder
+ *
+ * Copyright (c) 2005 Steve Underwood <steveu at coppice.org>
+ * Copyright (c) CMU 1993 Computer Science, Speech Group
+ * Chengxiang Lu and Alex Hauptmann
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+/**
+ * @file libavcodec/g722dec.c
+ *
+ * G.722 ADPCM audio codec
+ *
+ * This G.722 decoder is a bit-exact implementation of the ITU G.722 specification
+ * for all three specified bitrates - 64000bps, 56000bps and 48000bps.
+ * It passes the ITU tests.
+ *
+ * @note For the 56000bps and 48000bps bitrates, the respectively 7 and 6 bits
+ * codeword might be packed, so unpacking might be needed either
+ * internally or as a separate parser.
+ */
+
+#include <stdint.h>
+#include "avcodec.h"
+#include "mathops.h"
+
+typedef struct {
+ int bits_per_sample; ///< 6 for 48000kbps, 7 for 56000kbps, or 8 for 64000kbps
+
+ int16_t prev_samples[24]; ///< memory of past 24 received (decoded) samples
+
+ /**
+ * The band[0] and band[1] correspond respectively to the lower band and higher band.
+ */
+ struct G722Band {
+ int16_t s_predictor; ///< predictor output value
+ int32_t s_zero; ///< zero section output signal
+ int8_t part_reconst_mem[2]; ///< partially reconstructed signal memory
+ int16_t prev_qtzd_reconst; ///< previous quantized reconstructed signal
+ int16_t pole_mem[2]; ///< second-order pole section coefficient buffer
+ int32_t diff_mem[6]; ///< quantizer difference signal memory
+ int16_t zero_mem[6]; ///< Seventh-order zero section coefficient buffer
+ int16_t log_factor; ///< delayed logarithmic quantizer factor
+ int16_t scale_factor; ///< delayed quantizer scale factor
+ } band[2];
+} G722Context;
+
+
+static const int8_t sign_lookup[2] = { -1, 1 };
+
+static const int16_t ilb[32] = {
+ 2048, 2093, 2139, 2186, 2233, 2282, 2332, 2383,
+ 2435, 2489, 2543, 2599, 2656, 2714, 2774, 2834,
+ 2896, 2960, 3025, 3091, 3158, 3228, 3298, 3371,
+ 3444, 3520, 3597, 3676, 3756, 3838, 3922, 4008
+};
+static const int16_t wh[2] = { 798, -214 };
+static const int16_t qm2[4] = { -7408, -1616, 7408, 1616 };
+/**
+ * qm3[index] == wl[rl42[index]]
+ */
+static const int16_t qm3[16] = {
+ -60, 3042, 1198, 538, 334, 172, 58, -30,
+ 3042, 1198, 538, 334, 172, 58, -30, -60
+};
+static const int16_t qm4[16] = {
+ 0, -20456, -12896, -8968, -6288, -4240, -2584, -1200,
+ 20456, 12896, 8968, 6288, 4240, 2584, 1200, 0
+};
+
+/**
+ * quadrature mirror filter (QMF) coefficients
+ *
+ * ITU-T G.722 Table 11
+ */
+static const int16_t qmf_coeffs[12] = {
+ 3, -11, 12, 32, -210, 951, 3876, -805, 362, -156, 53, -11,
+};
+
+
+/**
+ * adaptive predictor
+ *
+ * @note On x86 using the MULL macro in a loop is slower than not using the macro.
+ */
+static void do_adaptive_prediction(struct G722Band *band, const int cur_diff)
+{
+ int sg[2], limit, i, cur_qtzd_reconst;
+
+ const int cur_part_reconst = band->s_zero + cur_diff < 0;
+
+ sg[0] = sign_lookup[cur_part_reconst != band->part_reconst_mem[0]];
+ sg[1] = sign_lookup[cur_part_reconst == band->part_reconst_mem[1]];
+ band->part_reconst_mem[1] = band->part_reconst_mem[0];
+ band->part_reconst_mem[0] = cur_part_reconst;
+
+ band->pole_mem[1] = av_clip((sg[0] * av_clip(band->pole_mem[0], -8191, 8191) >> 5) +
+ (sg[1] << 7) + MULL(band->pole_mem[1], 127, 7), -12288, 12288);
+
+ limit = 15360 - band->pole_mem[1];
+ band->pole_mem[0] = av_clip(-192 * sg[0] + MULL(band->pole_mem[0], 255, 8), -limit, limit);
+
+
+ if (cur_diff) {
+ for (i = 0; i < 6; i++)
+ band->zero_mem[i] = ((band->zero_mem[i]*255) >> 8) +
+ ((band->diff_mem[i]^cur_diff) < 0 ? -128 : 128);
+ } else
+ for (i = 0; i < 6; i++)
+ band->zero_mem[i] = (band->zero_mem[i]*255) >> 8;
+
+ for (i = 5; i > 0; i--)
+ band->diff_mem[i] = band->diff_mem[i-1];
+ band->diff_mem[0] = av_clip_int16(cur_diff << 1);
+
+ band->s_zero = 0;
+ for (i = 5; i >= 0; i--)
+ band->s_zero += (band->zero_mem[i]*band->diff_mem[i]) >> 15;
+
+
+ cur_qtzd_reconst = av_clip_int16((band->s_predictor + cur_diff) << 1);
+ band->s_predictor = av_clip_int16(band->s_zero +
+ MULL(band->pole_mem[0], cur_qtzd_reconst, 15) +
+ MULL(band->pole_mem[1], band->prev_qtzd_reconst, 15));
+ band->prev_qtzd_reconst = cur_qtzd_reconst;
+}
+
+static int inline scale(const int log_factor, int shift)
+{
+ const int wd1 = ilb[(log_factor >> 6) & 31];
+ shift -= log_factor >> 11;
+ return (shift < 0 ? wd1 << -shift : wd1 >> shift) << 2;
+}
+
+static void update_low_predictor(struct G722Band *band, const int ilow)
+{
+ do_adaptive_prediction(band, MULL(band->scale_factor, qm4[ilow], 15));
+
+ // quantizer adaptation
+ band->log_factor = av_clip(MULL(band->log_factor, 127, 7) + qm3[ilow], 0, 18432);
+ band->scale_factor = scale(band->log_factor, 8);
+}
+
+static void update_high_predictor(struct G722Band *band, const int dhigh, const int ihigh)
+{
+ do_adaptive_prediction(band, dhigh);
+
+ // quantizer adaptation
+ band->log_factor = av_clip(MULL(band->log_factor, 127, 7) + wh[ihigh&1], 0, 22528);
+ band->scale_factor = scale(band->log_factor, 10);
+}
+
+static void apply_qmf(int16_t *prev_samples, int *xout1, int *xout2)
+{
+ int i;
+
+ *xout1 = 0;
+ *xout2 = 0;
+ for (i = 0; i < 12; i++) {
+ MAC16(*xout2, prev_samples[2*i ], qmf_coeffs[i ]);
+ MAC16(*xout1, prev_samples[2*i+1], qmf_coeffs[11-i]);
+ }
+ memmove(prev_samples, prev_samples + 2, 22*sizeof(prev_samples[0]));
+}
+
+static av_cold int g722_init(AVCodecContext * avctx)
+{
+ G722Context *c = (G722Context *) avctx->priv_data;
+
+ if (avctx->channels != 1) {
+ av_log(avctx, AV_LOG_ERROR, "Only mono tracks are allowed.\n");
+ return -1;
+ }
+
+ switch (avctx->bit_rate) {
+ case 64000:
+ case 56000:
+ case 48000:
+ c->bits_per_sample = avctx->bit_rate/8000;
+ break;
+ default:
+ if (avctx->strict_std_compliance >= FF_COMPLIANCE_STRICT) {
+ av_log(avctx, AV_LOG_ERROR, "Unsupported bitrate [%d] only 48Kb, 56Kb and 64Kb are supported.\n", avctx->bit_rate);
+ return -1;
+ }
+ av_log(avctx, AV_LOG_WARNING, "Unsupported bitrate [%d], trying with 64Kb.\n", avctx->bit_rate);
+ avctx->bit_rate = 64000;
+ c->bits_per_sample = 8;
+ }
+
+ if (avctx->sample_rate != 8000 && avctx->sample_rate != 16000) {
+ av_log(avctx, AV_LOG_ERROR, "Unsupported sample rate [%d] only 8KHz and 16KHz are supported.\n", avctx->sample_rate);
+ return -1;
+ }
+
+ c->band[0].scale_factor = 32;
+ c->band[1].scale_factor = 8;
+
+ return 0;
+}
+
+#if CONFIG_ADPCM_G722_DECODER
+
+static const int16_t qm5[32] = {
+ -280, -280, -23352, -17560, -14120, -11664, -9752, -8184,
+ -6864, -5712, -4696, -3784, -2960, -2208, -1520, -880,
+ 23352, 17560, 14120, 11664, 9752, 8184, 6864, 5712,
+ 4696, 3784, 2960, 2208, 1520, 880, 280, -280
+};
+static const int16_t qm6[64] = {
+ -136, -136, -136, -136, -24808, -21904, -19008, -16704,
+ -14984, -13512, -12280, -11192, -10232, -9360, -8576, -7856,
+ -7192, -6576, -6000, -5456, -4944, -4464, -4008, -3576,
+ -3168, -2776, -2400, -2032, -1688, -1360, -1040, -728,
+ 24808, 21904, 19008, 16704, 14984, 13512, 12280, 11192,
+ 10232, 9360, 8576, 7856, 7192, 6576, 6000, 5456,
+ 4944, 4464, 4008, 3576, 3168, 2776, 2400, 2032,
+ 1688, 1360, 1040, 728, 432, 136, -432, -136
+};
+
+static const int16_t *qms[3] = { qm6, qm5, qm4 };
+
+static int g722_decode_frame(AVCodecContext *avctx, void *data, int *data_size, AVPacket *avpkt)
+{
+ G722Context *c = avctx->priv_data;
+ int16_t *out_buf = data;
+ const uint8_t *buf = avpkt->data;
+ int j, out_len = 0;
+ const int shift = 8 - c->bits_per_sample;
+ const int16_t *quantizer_table = qms[shift];
+
+ for (j = 0; j < avpkt->size; j++) {
+ const int ilow = buf[j] & (0x3F >> shift);
+ const int rlow = av_clip(MULL(c->band[0].scale_factor, quantizer_table[ilow], 15) +
+ c->band[0].s_predictor, -16384, 16383);
+
+ update_low_predictor(&c->band[0], ilow >> (2 - shift));
+
+ if (avctx->sample_rate == 16000) {
+ const int ihigh = (buf[j] >> (6 - shift)) & 0x03;
+ const int dhigh = MULL(c->band[1].scale_factor, qm2[ihigh], 15);
+ const int rhigh = av_clip(dhigh + c->band[1].s_predictor, -16384, 16383);
+ int xout1, xout2;
+
+ update_high_predictor(&c->band[1], dhigh, ihigh);
+
+ c->prev_samples[22] = rlow + rhigh;
+ c->prev_samples[23] = rlow - rhigh;
+ apply_qmf(c->prev_samples, &xout1, &xout2);
+ out_buf[out_len++] = av_clip_int16(xout1 >> 12);
+ out_buf[out_len++] = av_clip_int16(xout2 >> 12);
+ } else
+ out_buf[out_len++] = rlow;
+ }
+ *data_size = out_len << 1;
+ return avpkt->size;
+}
+
+AVCodec adpcm_g722_decoder = {
+ .name = "g722",
+ .type = CODEC_TYPE_AUDIO,
+ .id = CODEC_ID_ADPCM_G722,
+ .priv_data_size = sizeof(G722Context),
+ .init = g722_init,
+ .decode = g722_decode_frame,
+ .long_name = NULL_IF_CONFIG_SMALL("G.722 ADPCM"),
+};
+#endif
+
+#if CONFIG_ADPCM_G722_ENCODER
+static const int16_t q6[29] = {
+ 35, 72, 110, 150, 190, 233, 276, 323,
+ 370, 422, 473, 530, 587, 650, 714, 786,
+ 858, 940, 1023, 1121, 1219, 1339, 1458, 1612,
+ 1765, 1980, 2195, 2557, 2919
+};
+
+static int g722_encode_frame(AVCodecContext *avctx,
+ uint8_t *dst, int buf_size, void *data)
+{
+ G722Context *c = avctx->priv_data;
+ const int16_t *samples = data;
+
+ int diff, limit;
+ int i, j;
+
+ for (j = 0; j < buf_size; ) {
+ int xlow, rlow;
+ if (avctx->sample_rate == 16000) {
+ int xout1, xout2, xhigh, diff, pred, index;
+
+ c->prev_samples[22] = samples[j++];
+ c->prev_samples[23] = samples[j++];
+ apply_qmf(c->prev_samples, &xout1, &xout2);
+ xlow = (xout1 + xout2) >> 14;
+ xhigh = (xout1 - xout2) >> 14;
+
+ diff = av_clip_int16(xhigh - c->band[1].s_predictor);
+ pred = MULL(564, c->band[1].scale_factor, 12);
+ index = diff >= 0 ? (diff < pred) + 2
+ : diff >= -pred;
+
+ update_high_predictor(&c->band[1], MULL(c->band[1].scale_factor, qm2[index], 15), index);
+
+ *dst = (index << 6);
+ } else
+ xlow = samples[j++];
+
+ diff = av_clip_int16(xlow - c->band[0].s_predictor);
+ limit = diff >= 0 ? diff : -(diff + 1);
+ for (i = 0; i < 29 && limit >= (q6[i]*c->band[0].scale_factor) >> 12; i++)
+ ;
+ *dst |=
+ rlow = (diff < 0 ? (i < 2 ? 63 : 33) : 61) - i;
+
+ update_low_predictor(&c->band[0], rlow >> 2);
+
+ *dst++ >>= 8 - c->bits_per_sample;
+ }
+ return avctx->sample_rate == 8000 ? buf_size : buf_size >> 1;
+}
+
+AVCodec adpcm_g722_encoder = {
+ .name = "g722",
+ .type = CODEC_TYPE_AUDIO,
+ .id = CODEC_ID_ADPCM_G722,
+ .priv_data_size = sizeof(G722Context),
+ .init = g722_init,
+ .encode = g722_encode_frame,
+ .long_name = NULL_IF_CONFIG_SMALL("G.722 ADPCM"),
+ .sample_fmts = (enum SampleFormat[]){SAMPLE_FMT_S16,SAMPLE_FMT_NONE},
+};
+
+#endif
-------------- next part --------------
Index: libavformat/avformat.h
===================================================================
--- libavformat/avformat.h (revision 18382)
+++ libavformat/avformat.h (working copy)
@@ -22,7 +22,7 @@
#define AVFORMAT_AVFORMAT_H
#define LIBAVFORMAT_VERSION_MAJOR 52
-#define LIBAVFORMAT_VERSION_MINOR 32
+#define LIBAVFORMAT_VERSION_MINOR 33
#define LIBAVFORMAT_VERSION_MICRO 0
#define LIBAVFORMAT_VERSION_INT AV_VERSION_INT(LIBAVFORMAT_VERSION_MAJOR, \
Index: libavformat/allformats.c
===================================================================
--- libavformat/allformats.c (revision 18382)
+++ libavformat/allformats.c (working copy)
@@ -83,6 +83,7 @@
REGISTER_MUXDEMUX (FLV, flv);
REGISTER_DEMUXER (FOURXM, fourxm);
REGISTER_MUXER (FRAMECRC, framecrc);
+ REGISTER_MUXDEMUX (G722, g722);
REGISTER_MUXER (GIF, gif);
REGISTER_DEMUXER (GSM, gsm);
REGISTER_MUXDEMUX (GXF, gxf);
Index: libavformat/raw.c
===================================================================
--- libavformat/raw.c (revision 18382)
+++ libavformat/raw.c (working copy)
@@ -782,6 +782,36 @@
};
#endif
+#if CONFIG_G722_DEMUXER
+AVInputFormat g722_demuxer = {
+ "g722",
+ NULL_IF_CONFIG_SMALL("raw G.722"),
+ 0,
+ NULL,
+ raw_read_header,
+ ff_raw_read_partial_packet,
+ .flags= AVFMT_GENERIC_INDEX,
+ .extensions = "g722,722",
+ .value = CODEC_ID_ADPCM_G722,
+};
+#endif
+
+#if CONFIG_G722_MUXER
+AVOutputFormat g722_muxer = {
+ "g722",
+ NULL_IF_CONFIG_SMALL("raw G.722"),
+ "audio/G722",
+ "g722",
+ 0,
+ CODEC_ID_ADPCM_G722,
+ CODEC_ID_NONE,
+ NULL,
+ raw_write_packet,
+ .flags= AVFMT_NOTIMESTAMPS,
+};
+#endif
+
+
#if CONFIG_GSM_DEMUXER
AVInputFormat gsm_demuxer = {
"gsm",
More information about the ffmpeg-devel
mailing list