summaryrefslogtreecommitdiffstats
path: root/libavfilter/af_silencedetect.c
blob: dbd9f5ffd76698ee8b9ef017f7ed92dda633c630 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
/*
 * Copyright (c) 2012 Clément Bœsch <ubitux@gmail.com>
 *
 * 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
 * Audio silence detector
 */

#include <float.h> /* DBL_MAX */

#include "libavutil/channel_layout.h"
#include "libavutil/opt.h"
#include "libavutil/timestamp.h"
#include "audio.h"
#include "formats.h"
#include "avfilter.h"
#include "internal.h"

typedef struct {
    const AVClass *class;
    double noise;               ///< noise amplitude ratio
    double duration;            ///< minimum duration of silence until notification
    int64_t nb_null_samples;    ///< current number of continuous zero samples
    int64_t start;              ///< if silence is detected, this value contains the time of the first zero sample
    int last_sample_rate;       ///< last sample rate to check for sample rate changes
} SilenceDetectContext;

#define OFFSET(x) offsetof(SilenceDetectContext, x)
#define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_AUDIO_PARAM
static const AVOption silencedetect_options[] = {
    { "n",         "set noise tolerance",              OFFSET(noise),     AV_OPT_TYPE_DOUBLE, {.dbl=0.001},          0, DBL_MAX,  FLAGS },
    { "noise",     "set noise tolerance",              OFFSET(noise),     AV_OPT_TYPE_DOUBLE, {.dbl=0.001},          0, DBL_MAX,  FLAGS },
    { "d",         "set minimum duration in seconds",  OFFSET(duration),  AV_OPT_TYPE_DOUBLE, {.dbl=2.},             0, 24*60*60, FLAGS },
    { "duration",  "set minimum duration in seconds",  OFFSET(duration),  AV_OPT_TYPE_DOUBLE, {.dbl=2.},             0, 24*60*60, FLAGS },
    { NULL },
};

AVFILTER_DEFINE_CLASS(silencedetect);

static av_cold int init(AVFilterContext *ctx, const char *args)
{
    int ret;
    SilenceDetectContext *silence = ctx->priv;

    silence->class = &silencedetect_class;
    av_opt_set_defaults(silence);

    if ((ret = av_set_options_string(silence, args, "=", ":")) < 0)
        return ret;

    av_opt_free(silence);

    return 0;
}

static char *get_metadata_val(AVFrame *insamples, const char *key)
{
    AVDictionaryEntry *e = av_dict_get(insamples->metadata, key, NULL, 0);
    return e && e->value ? e->value : NULL;
}

static int filter_frame(AVFilterLink *inlink, AVFrame *insamples)
{
    int i;
    SilenceDetectContext *silence = inlink->dst->priv;
    const int nb_channels           = av_get_channel_layout_nb_channels(inlink->channel_layout);
    const int srate                 = inlink->sample_rate;
    const int nb_samples            = insamples->nb_samples     * nb_channels;
    const int64_t nb_samples_notify = srate * silence->duration * nb_channels;

    // scale number of null samples to the new sample rate
    if (silence->last_sample_rate && silence->last_sample_rate != srate)
        silence->nb_null_samples =
            srate * silence->nb_null_samples / silence->last_sample_rate;
    silence->last_sample_rate = srate;

    // TODO: support more sample formats
    // TODO: document metadata
    if (insamples->format == AV_SAMPLE_FMT_DBL) {
        double *p = (double *)insamples->data[0];

        for (i = 0; i < nb_samples; i++, p++) {
            if (*p < silence->noise && *p > -silence->noise) {
                if (!silence->start) {
                    silence->nb_null_samples++;
                    if (silence->nb_null_samples >= nb_samples_notify) {
                        silence->start = insamples->pts - (int64_t)(silence->duration / av_q2d(inlink->time_base) + .5);
                        av_dict_set(&insamples->metadata, "lavfi.silence_start",
                                    av_ts2timestr(silence->start, &inlink->time_base), 0);
                        av_log(silence, AV_LOG_INFO, "silence_start: %s\n",
                               get_metadata_val(insamples, "lavfi.silence_start"));
                    }
                }
            } else {
                if (silence->start) {
                    av_dict_set(&insamples->metadata, "lavfi.silence_end",
                                av_ts2timestr(insamples->pts, &inlink->time_base), 0);
                    av_dict_set(&insamples->metadata, "lavfi.silence_duration",
                                av_ts2timestr(insamples->pts - silence->start, &inlink->time_base), 0);
                    av_log(silence, AV_LOG_INFO,
                           "silence_end: %s | silence_duration: %s\n",
                           get_metadata_val(insamples, "lavfi.silence_end"),
                           get_metadata_val(insamples, "lavfi.silence_duration"));
                }
                silence->nb_null_samples = silence->start = 0;
            }
        }
    }

    return ff_filter_frame(inlink->dst->outputs[0], insamples);
}

static int query_formats(AVFilterContext *ctx)
{
    AVFilterFormats *formats = NULL;
    AVFilterChannelLayouts *layouts = NULL;
    static const enum AVSampleFormat sample_fmts[] = {
        AV_SAMPLE_FMT_DBL,
        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 const AVFilterPad silencedetect_inputs[] = {
    {
        .name             = "default",
        .type             = AVMEDIA_TYPE_AUDIO,
        .get_audio_buffer = ff_null_get_audio_buffer,
        .filter_frame     = filter_frame,
    },
    { NULL }
};

static const AVFilterPad silencedetect_outputs[] = {
    {
        .name = "default",
        .type = AVMEDIA_TYPE_AUDIO,
    },
    { NULL }
};

AVFilter avfilter_af_silencedetect = {
    .name          = "silencedetect",
    .description   = NULL_IF_CONFIG_SMALL("Detect silence."),
    .priv_size     = sizeof(SilenceDetectContext),
    .init          = init,
    .query_formats = query_formats,
    .inputs        = silencedetect_inputs,
    .outputs       = silencedetect_outputs,
    .priv_class    = &silencedetect_class,
};
OpenPOWER on IntegriCloud