[FFmpeg-devel] [PATCH] lavfi: add aecho filter

Paul B Mahol onemda at gmail.com
Tue Jul 9 16:53:14 CEST 2013


Signed-off-by: Paul B Mahol <onemda at gmail.com>
---
 doc/filters.texi         |  29 +++++
 libavfilter/Makefile     |   1 +
 libavfilter/af_aecho.c   | 297 +++++++++++++++++++++++++++++++++++++++++++++++
 libavfilter/allfilters.c |   1 +
 4 files changed, 328 insertions(+)
 create mode 100644 libavfilter/af_aecho.c

diff --git a/doc/filters.texi b/doc/filters.texi
index 234ff2e..9472675 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -347,6 +347,35 @@ aconvert=u8:auto
 @end example
 @end itemize
 
+ at section aecho
+
+Apply echoing to the input audio.
+
+Echoes are reflected sound and can occur naturally amongst mountains
+(and sometimes large buildings) when talking or shouting; digital echo
+effects emulate this behaviour and are often used to help fill out the
+sound of a single instrument or vocal. The time difference between the
+original signal and the reflection is the @code{delay}, and the
+loudness of the reflected signal is the @code{decay}.
+Multiple echoes can have different delays and decays.
+
+A description of the accepted parameters follows.
+
+ at table @option
+ at item in_gain
+Set input volume of reflected signal.
+
+ at item out_gain
+Set output volume of reflected signal.
+
+ at item delay1..7
+Set time interval in miliseconds between original signal and reflection.
+
+ at item decay1..7
+Loudness of reflected signal.
+
+ at end table
+
 @section afade
 
 Apply fade-in/out effect to input audio.
diff --git a/libavfilter/Makefile b/libavfilter/Makefile
index cf76ee1..306b24c 100644
--- a/libavfilter/Makefile
+++ b/libavfilter/Makefile
@@ -52,6 +52,7 @@ OBJS-$(CONFIG_AVFORMAT)                      += lavfutils.o
 OBJS-$(CONFIG_SWSCALE)                       += lswsutils.o
 
 OBJS-$(CONFIG_ACONVERT_FILTER)               += af_aconvert.o
+OBJS-$(CONFIG_AECHO_FILTER)                  += af_aecho.o
 OBJS-$(CONFIG_AFADE_FILTER)                  += af_afade.o
 OBJS-$(CONFIG_AFORMAT_FILTER)                += af_aformat.o
 OBJS-$(CONFIG_AINTERLEAVE_FILTER)            += f_interleave.o
diff --git a/libavfilter/af_aecho.c b/libavfilter/af_aecho.c
new file mode 100644
index 0000000..9d4010d
--- /dev/null
+++ b/libavfilter/af_aecho.c
@@ -0,0 +1,297 @@
+/*
+ * Copyright (c) 2013 Paul B Mahol
+ *
+ * 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
+ *
+ */
+
+#include "libavutil/avstring.h"
+#include "libavutil/opt.h"
+#include "libavutil/samplefmt.h"
+#include "libavutil/avassert.h"
+#include "avfilter.h"
+#include "audio.h"
+#include "internal.h"
+
+#define MAX_ECHOS 7
+
+typedef struct AudioEchoContext {
+    const AVClass *class;
+    float in_gain, out_gain;
+    float delay[MAX_ECHOS], decay[MAX_ECHOS];
+    int nb_echos;
+    int delay_index;
+    uint8_t **delayptrs;
+    int max_samples, fade_out;
+    int samples[MAX_ECHOS];
+    int64_t next_pts;
+
+    void (*echo_samples)(struct AudioEchoContext *ctx, uint8_t **delayptrs,
+                         uint8_t * const *src, uint8_t **dst,
+                         int nb_samples, int channels);
+} AudioEchoContext;
+
+#define OFFSET(x) offsetof(AudioEchoContext, x)
+#define A AV_OPT_FLAG_AUDIO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
+
+static const AVOption aecho_options[] = {
+    { "in_gain",  "", OFFSET(in_gain),  AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "out_gain", "", OFFSET(out_gain), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "delay1",   "", OFFSET(delay[0]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 90000, A },
+    { "decay1",   "", OFFSET(decay[0]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "delay2",   "", OFFSET(delay[1]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 90000, A },
+    { "decay2",   "", OFFSET(decay[1]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "delay3",   "", OFFSET(delay[2]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 90000, A },
+    { "decay3",   "", OFFSET(decay[2]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "delay4",   "", OFFSET(delay[3]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 90000, A },
+    { "decay4",   "", OFFSET(decay[3]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "delay5",   "", OFFSET(delay[4]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 90000, A },
+    { "decay5",   "", OFFSET(decay[4]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "delay6",   "", OFFSET(delay[5]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 90000, A },
+    { "decay6",   "", OFFSET(decay[5]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { "delay7",   "", OFFSET(delay[6]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 90000, A },
+    { "decay7",   "", OFFSET(decay[6]), AV_OPT_TYPE_FLOAT, {.dbl=0}, 0, 1, A },
+    { NULL },
+};
+
+AVFILTER_DEFINE_CLASS(aecho);
+
+static av_cold int init(AVFilterContext *ctx)
+{
+    AudioEchoContext *s = ctx->priv;
+    int i;
+
+    for (i = 0; i < MAX_ECHOS; i++) {
+        if (!s->delay[i] || !s->decay[i])
+            break;
+    }
+    s->nb_echos = i;
+    if (!s->nb_echos) {
+        av_log(ctx, AV_LOG_ERROR, "at least one decay & delay must be set");
+        return AVERROR(EINVAL);
+    }
+
+    s->next_pts = AV_NOPTS_VALUE;
+
+    return 0;
+}
+
+static int query_formats(AVFilterContext *ctx)
+{
+    AVFilterChannelLayouts *layouts;
+    AVFilterFormats *formats;
+    static const enum AVSampleFormat sample_fmts[] = {
+        AV_SAMPLE_FMT_S16P, AV_SAMPLE_FMT_S32P,
+        AV_SAMPLE_FMT_FLTP, AV_SAMPLE_FMT_DBLP,
+        AV_SAMPLE_FMT_NONE
+    };
+
+    layouts = ff_all_channel_layouts();
+    if (!layouts)
+        return AVERROR(ENOMEM);
+    ff_set_common_channel_layouts(ctx, layouts);
+
+    formats = ff_make_format_list(sample_fmts);
+    if (!formats)
+        return AVERROR(ENOMEM);
+    ff_set_common_formats(ctx, formats);
+
+    formats = ff_all_samplerates();
+    if (!formats)
+        return AVERROR(ENOMEM);
+    ff_set_common_samplerates(ctx, formats);
+
+    return 0;
+}
+
+static av_cold void uninit(AVFilterContext *ctx)
+{
+    AudioEchoContext *s = ctx->priv;
+
+    if (s->delayptrs)
+        av_freep(s->delayptrs[0]);
+    av_freep(&s->delayptrs);
+}
+
+#define MOD(a, b) (((a) >= (b)) ? (a) - (b) : (a))
+
+#define ECHO(name, type, min, max)                                          \
+static void echo_samples_## name ##p(AudioEchoContext *ctx,                 \
+                                     uint8_t **delayptrs,                   \
+                                     uint8_t * const *src, uint8_t **dst,   \
+                                     int nb_samples, int channels)          \
+{                                                                           \
+    const double out_gain = ctx->out_gain;                                  \
+    const double in_gain = ctx->in_gain;                                    \
+    const int nb_echos = ctx->nb_echos;                                     \
+    const int max_samples = ctx->max_samples;                               \
+    int i, j, chan, index;                                                  \
+                                                                            \
+    for (chan = 0; chan < channels; chan++) {                               \
+        const type *s = (type *)src[chan];                                  \
+        type *d = (type *)dst[chan];                                        \
+        type *dbuf = (type *)delayptrs[chan];                               \
+                                                                            \
+        index = ctx->delay_index;                                           \
+        for (i = 0; i < nb_samples; i++, s++, d++) {                        \
+            double out, in;                                                 \
+                                                                            \
+            in = *s;                                                        \
+            out = in * in_gain;                                             \
+            for (j = 0; j < nb_echos; j++) {                                \
+                int ix = index + max_samples - ctx->samples[j];             \
+                ix = MOD(ix, max_samples);                                  \
+                out += dbuf[ix] * ctx->decay[j];                            \
+            }                                                               \
+            out *= out_gain;                                                \
+                                                                            \
+            *d = av_clipd(out, min, max);                                   \
+            dbuf[index] = in;                                               \
+                                                                            \
+            index = MOD(index + 1, max_samples);                            \
+        }                                                                   \
+    }                                                                       \
+    ctx->delay_index = index;                                               \
+}
+
+ECHO(dbl, double,  -1.0,      1.0      )
+ECHO(flt, float,   -1.0,      1.0      )
+ECHO(s16, int16_t, INT16_MIN, INT16_MAX)
+ECHO(s32, int32_t, INT32_MIN, INT32_MAX)
+
+static int config_output(AVFilterLink *outlink)
+{
+    AVFilterContext *ctx = outlink->src;
+    AudioEchoContext *s = ctx->priv;
+    float volume = 1.0;
+    int i;
+
+    for (i = 0; i < s->nb_echos; i++) {
+        s->samples[i] = s->delay[i] * outlink->sample_rate / 1000.0;
+        s->max_samples = FFMAX(s->max_samples, s->samples[i]);
+        volume += s->decay[i];
+    }
+    s->fade_out = s->max_samples;
+
+    if (volume * s->in_gain * s->out_gain > 1.0)
+        av_log(ctx, AV_LOG_WARNING,
+               "out_gain %f can cause saturation of output\n", s->out_gain);
+
+    switch (outlink->format) {
+    case AV_SAMPLE_FMT_DBLP: s->echo_samples = echo_samples_dblp; break;
+    case AV_SAMPLE_FMT_FLTP: s->echo_samples = echo_samples_fltp; break;
+    case AV_SAMPLE_FMT_S16P: s->echo_samples = echo_samples_s16p; break;
+    case AV_SAMPLE_FMT_S32P: s->echo_samples = echo_samples_s32p; break;
+    }
+
+    uninit(ctx);
+    return av_samples_alloc_array_and_samples(&s->delayptrs, NULL,
+                                              outlink->channels,
+                                              s->max_samples,
+                                              outlink->format, 0);
+}
+
+static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
+{
+    AVFilterContext *ctx = inlink->dst;
+    AudioEchoContext *s = ctx->priv;
+    AVFrame *out_frame;
+
+    if (av_frame_is_writable(frame)) {
+        out_frame = frame;
+    } else {
+        out_frame = ff_get_audio_buffer(inlink, frame->nb_samples);
+        if (!out_frame)
+            return AVERROR(ENOMEM);
+        av_frame_copy_props(out_frame, frame);
+    }
+
+    s->echo_samples(s, s->delayptrs, frame->data, out_frame->data,
+                    frame->nb_samples, inlink->channels);
+
+    if (frame != out_frame)
+        av_frame_free(&frame);
+
+    s->next_pts = frame->pts + av_rescale_q(frame->nb_samples, (AVRational){1, inlink->sample_rate}, inlink->time_base);
+    return ff_filter_frame(ctx->outputs[0], out_frame);
+}
+
+static int request_frame(AVFilterLink *outlink)
+{
+    AVFilterContext *ctx = outlink->src;
+    AudioEchoContext *s = ctx->priv;
+    int ret;
+
+    ret = ff_request_frame(ctx->inputs[0]);
+
+    if (ret == AVERROR_EOF && !ctx->is_disabled && s->fade_out) {
+        int nb_samples = FFMIN(s->fade_out, 2048);
+        AVFrame *frame;
+
+        frame = ff_get_audio_buffer(outlink, nb_samples);
+        if (!frame)
+            return AVERROR(ENOMEM);
+        s->fade_out -= nb_samples;
+
+        av_samples_set_silence(frame->extended_data, 0,
+                               frame->nb_samples,
+                               outlink->channels,
+                               frame->format);
+
+        s->echo_samples(s, s->delayptrs, frame->data, frame->data,
+                        frame->nb_samples, outlink->channels);
+
+        frame->pts = s->next_pts;
+        if (s->next_pts != AV_NOPTS_VALUE)
+            s->next_pts += av_rescale_q(nb_samples, (AVRational){1, outlink->sample_rate}, outlink->time_base);
+
+        return ff_filter_frame(outlink, frame);
+    }
+
+    return ret;
+}
+
+static const AVFilterPad aecho_inputs[] = {
+    {
+        .name         = "default",
+        .type         = AVMEDIA_TYPE_AUDIO,
+        .filter_frame = filter_frame,
+    },
+    { NULL },
+};
+
+static const AVFilterPad aecho_outputs[] = {
+    {
+        .name          = "default",
+        .request_frame = request_frame,
+        .config_props  = config_output,
+        .type          = AVMEDIA_TYPE_AUDIO,
+    },
+    { NULL },
+};
+
+AVFilter avfilter_af_aecho = {
+    .name          = "aecho",
+    .description   = NULL_IF_CONFIG_SMALL("Add echoing to the audio."),
+    .query_formats = query_formats,
+    .priv_size     = sizeof(AudioEchoContext),
+    .priv_class    = &aecho_class,
+    .init          = init,
+    .uninit        = uninit,
+    .inputs        = aecho_inputs,
+    .outputs       = aecho_outputs,
+};
diff --git a/libavfilter/allfilters.c b/libavfilter/allfilters.c
index 9a11feb..26472f8 100644
--- a/libavfilter/allfilters.c
+++ b/libavfilter/allfilters.c
@@ -48,6 +48,7 @@ void avfilter_register_all(void)
 #if FF_API_ACONVERT_FILTER
     REGISTER_FILTER(ACONVERT,       aconvert,       af);
 #endif
+    REGISTER_FILTER(AECHO,          aecho,          af);
     REGISTER_FILTER(AFADE,          afade,          af);
     REGISTER_FILTER(AFORMAT,        aformat,        af);
     REGISTER_FILTER(AINTERLEAVE,    ainterleave,    af);
-- 
1.7.11.2



More information about the ffmpeg-devel mailing list