libspeexenc.c File Reference

libspeex Speex audio encoder More...

#include <speex/speex.h>
#include <speex/speex_header.h>
#include <speex/speex_stereo.h>
#include "libavutil/channel_layout.h"
#include "libavutil/common.h"
#include "libavutil/opt.h"
#include "avcodec.h"
#include "internal.h"
#include "audio_frame_queue.h"

Go to the source code of this file.

Data Structures
struct	LibSpeexEncContext

Macros
#define	OFFSET(x)   offsetof(LibSpeexEncContext, x)
#define	AE   AV_OPT_FLAG_AUDIO_PARAM | AV_OPT_FLAG_ENCODING_PARAM

Functions
static av_cold void	print_enc_params (AVCodecContext *avctx, LibSpeexEncContext *s)
static av_cold int	encode_init (AVCodecContext *avctx)
static int	encode_frame (AVCodecContext *avctx, AVPacket *avpkt, const AVFrame *frame, int *got_packet_ptr)
static av_cold int	encode_close (AVCodecContext *avctx)

Variables
static const AVOption	options []
static const AVClass	speex_class
static const AVCodecDefault	defaults []
AVCodec	ff_libspeex_encoder

Detailed Description

libspeex Speex audio encoder

Usage Guide This explains the values that need to be set prior to initialization in order to control various encoding parameters.

Channels Speex only supports mono or stereo, so avctx->channels must be set to 1 or 2.

Sample Rate / Encoding Mode Speex has 3 modes, each of which uses a specific sample rate. narrowband : 8 kHz wideband : 16 kHz ultra-wideband : 32 kHz avctx->sample_rate must be set to one of these 3 values. This will be used to set the encoding mode.

Rate Control VBR mode is turned on by setting CODEC_FLAG_QSCALE in avctx->flags. avctx->global_quality is used to set the encoding quality. For CBR mode, avctx->bit_rate can be used to set the constant bitrate. Alternatively, the 'cbr_quality' option can be set from 0 to 10 to set a constant bitrate based on quality. For ABR mode, set avctx->bit_rate and set the 'abr' option to 1. Approx. Bitrate Range: narrowband : 2400 - 25600 bps wideband : 4000 - 43200 bps ultra-wideband : 4400 - 45200 bps

Complexity Encoding complexity is controlled by setting avctx->compression_level. The valid range is 0 to 10. A higher setting gives generally better quality at the expense of encoding speed. This does not affect the bit rate.

Frames-per-Packet The encoder defaults to using 1 frame-per-packet. However, it is sometimes desirable to use multiple frames-per-packet to reduce the amount of container overhead. This can be done by setting the 'frames_per_packet' option to a value 1 to 8.

Optional features Speex encoder supports several optional features, which can be useful for some conditions.

Voice Activity Detection When enabled, voice activity detection detects whether the audio being encoded is speech or silence/background noise. VAD is always implicitly activated when encoding in VBR, so the option is only useful in non-VBR operation. In this case, Speex detects non-speech periods and encodes them with just enough bits to reproduce the background noise.

Discontinuous Transmission (DTX) DTX is an addition to VAD/VBR operation, that allows to stop transmitting completely when the background noise is stationary. In file-based operation only 5 bits are used for such frames.

Definition in file libspeexenc.c.

Macro Definition Documentation

#define OFFSET

(

x

)

offsetof(LibSpeexEncContext, x)

Definition at line 326 of file libspeexenc.c.

#define AE   AV_OPT_FLAG_AUDIO_PARAM | AV_OPT_FLAG_ENCODING_PARAM

Definition at line 327 of file libspeexenc.c.

Function Documentation

static av_cold void print_enc_params ( AVCodecContext *  avctx, LibSpeexEncContext *  s  )

static

Definition at line 111 of file libspeexenc.c.

Referenced by encode_init().

static av_cold int encode_init ( AVCodecContext *  avctx )

static

Definition at line 145 of file libspeexenc.c.

static int encode_frame ( AVCodecContext *  avctx, AVPacket *  avpkt, const AVFrame *  frame, int *  got_packet_ptr  )

static

Definition at line 268 of file libspeexenc.c.

static av_cold int encode_close ( AVCodecContext *  avctx )

static

Definition at line 313 of file libspeexenc.c.

Variable Documentation

const AVOption options[]

static

Initial value:

= {
    { "abr",               "Use average bit rate",                      OFFSET(abr),               AV_OPT_TYPE_INT, { .i64 = 0 }, 0,   1, AE },
    { "cbr_quality",       "Set quality value (0 to 10) for CBR",       OFFSET(cbr_quality),       AV_OPT_TYPE_INT, { .i64 = 8 }, 0,  10, AE },
    { "frames_per_packet", "Number of frames to encode in each packet", OFFSET(frames_per_packet), AV_OPT_TYPE_INT, { .i64 = 1 }, 1,   8, AE },
    { "vad",               "Voice Activity Detection",                  OFFSET(vad),               AV_OPT_TYPE_INT, { .i64 = 0 }, 0,   1, AE },
    { "dtx",               "Discontinuous Transmission",                OFFSET(dtx),               AV_OPT_TYPE_INT, { .i64 = 0 }, 0,   1, AE },
    { NULL },
}

Definition at line 328 of file libspeexenc.c.

const AVClass speex_class

static

Initial value:

= {
    .class_name = "libspeex",
    .item_name  = av_default_item_name,
    .option     = options,
    .version    = LIBAVUTIL_VERSION_INT,
}

Definition at line 337 of file libspeexenc.c.

const AVCodecDefault defaults[]

static

Initial value:

= {
    { "b",                 "0" },
    { "compression_level", "3" },
    { NULL },
}

Definition at line 344 of file libspeexenc.c.

AVCodec ff_libspeex_encoder

Initial value:

= {
    .name           = "libspeex",
    .long_name      = NULL_IF_CONFIG_SMALL("libspeex Speex"),
    .type           = AVMEDIA_TYPE_AUDIO,
    .id             = AV_CODEC_ID_SPEEX,
    .priv_data_size = sizeof(LibSpeexEncContext),
    .init           = encode_init,
    .encode2        = encode_frame,
    .close          = encode_close,
    .capabilities   = CODEC_CAP_DELAY,
    .sample_fmts    = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_S16,
                                                     AV_SAMPLE_FMT_NONE },
    .channel_layouts = (const uint64_t[]){ AV_CH_LAYOUT_MONO,
                                           AV_CH_LAYOUT_STEREO,
                                           0 },
    .supported_samplerates = (const int[]){ 8000, 16000, 32000, 0 },
    .priv_class     = &speex_class,
    .defaults       = defaults,
}

Definition at line 350 of file libspeexenc.c.