* used to set the encoding mode.
*
* Rate Control
- * VBR mode is turned on by setting CODEC_FLAG_QSCALE in avctx->flags.
+ * VBR mode is turned on by setting AV_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
* 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.
*/
#include <speex/speex.h>
#include <speex/speex_header.h>
#include <speex/speex_stereo.h>
-#include "libavutil/audioconvert.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"
-typedef struct {
+typedef struct LibSpeexEncContext {
AVClass *class; ///< AVClass for private options
SpeexBits bits; ///< libspeex bitwriter context
SpeexHeader header; ///< libspeex header struct
float vbr_quality; ///< VBR quality 0.0 to 10.0
int cbr_quality; ///< CBR quality 0 to 10
int abr; ///< flag to enable ABR
+ int vad; ///< flag to enable VAD
+ int dtx; ///< flag to enable DTX
int pkt_frame_count; ///< frame count for the current packet
AudioFrameQueue afq; ///< frame queue
} LibSpeexEncContext;
s->frames_per_packet);
av_log(avctx, AV_LOG_DEBUG, "packet size: %d\n",
avctx->frame_size * s->frames_per_packet);
+ av_log(avctx, AV_LOG_DEBUG, "voice activity detection: %d\n", s->vad);
+ av_log(avctx, AV_LOG_DEBUG, "discontinuous transmission: %d\n", s->dtx);
}
static av_cold int encode_init(AVCodecContext *avctx)
speex_init_header(&s->header, avctx->sample_rate, avctx->channels, mode);
/* rate control method and parameters */
- if (avctx->flags & CODEC_FLAG_QSCALE) {
+ if (avctx->flags & AV_CODEC_FLAG_QSCALE) {
/* VBR */
s->header.vbr = 1;
+ s->vad = 1; /* VAD is always implicitly activated for VBR */
speex_encoder_ctl(s->enc_state, SPEEX_SET_VBR, &s->header.vbr);
s->vbr_quality = av_clipf(avctx->global_quality / (float)FF_QP2LAMBDA,
0.0f, 10.0f);
avctx->bit_rate = s->header.bitrate + (avctx->channels == 2 ? 800 : 0);
}
+ /* VAD is activated with VBR or can be turned on by itself */
+ if (s->vad)
+ speex_encoder_ctl(s->enc_state, SPEEX_SET_VAD, &s->vad);
+
+ /* Activiting Discontinuous Transmission */
+ if (s->dtx) {
+ speex_encoder_ctl(s->enc_state, SPEEX_SET_DTX, &s->dtx);
+ if (!(s->abr || s->vad || s->header.vbr))
+ av_log(avctx, AV_LOG_WARNING, "DTX is not much of use without ABR, VAD or VBR\n");
+ }
+
/* set encoding complexity */
if (avctx->compression_level > FF_COMPRESSION_DEFAULT) {
complexity = av_clip(avctx->compression_level, 0, 10);
s->header.frames_per_packet = s->frames_per_packet;
/* set encoding delay */
- speex_encoder_ctl(s->enc_state, SPEEX_GET_LOOKAHEAD, &avctx->delay);
+ speex_encoder_ctl(s->enc_state, SPEEX_GET_LOOKAHEAD, &avctx->initial_padding);
ff_af_queue_init(avctx, &s->afq);
/* create header packet bytes from header struct */
below with speex_header_free() */
header_data = speex_header_to_packet(&s->header, &header_size);
- /* allocate extradata and coded_frame */
- avctx->extradata = av_malloc(header_size + FF_INPUT_BUFFER_PADDING_SIZE);
+ /* allocate extradata */
+ avctx->extradata = av_malloc(header_size + AV_INPUT_BUFFER_PADDING_SIZE);
if (!avctx->extradata) {
speex_header_free(header_data);
speex_encoder_destroy(s->enc_state);
av_log(avctx, AV_LOG_ERROR, "memory allocation error\n");
return AVERROR(ENOMEM);
}
-#if FF_API_OLD_ENCODE_AUDIO
- avctx->coded_frame = avcodec_alloc_frame();
- if (!avctx->coded_frame) {
- av_freep(&avctx->extradata);
- speex_header_free(header_data);
- speex_encoder_destroy(s->enc_state);
- av_log(avctx, AV_LOG_ERROR, "memory allocation error\n");
- return AVERROR(ENOMEM);
- }
-#endif
/* copy header packet to extradata */
memcpy(avctx->extradata, header_data, header_size);
speex_encode_stereo_int(samples, s->header.frame_size, &s->bits);
speex_encode_int(s->enc_state, samples, &s->bits);
s->pkt_frame_count++;
- if ((ret = ff_af_queue_add(&s->afq, frame) < 0))
+ if ((ret = ff_af_queue_add(&s->afq, frame)) < 0)
return ret;
} else {
/* handle end-of-stream */
speex_encoder_destroy(s->enc_state);
ff_af_queue_close(&s->afq);
-#if FF_API_OLD_ENCODE_AUDIO
- av_freep(&avctx->coded_frame);
-#endif
av_freep(&avctx->extradata);
return 0;
#define OFFSET(x) offsetof(LibSpeexEncContext, x)
#define AE AV_OPT_FLAG_AUDIO_PARAM | AV_OPT_FLAG_ENCODING_PARAM
static const AVOption options[] = {
- { "abr", "Use average bit rate", OFFSET(abr), AV_OPT_TYPE_INT, { 0 }, 0, 1, AE },
- { "cbr_quality", "Set quality value (0 to 10) for CBR", OFFSET(cbr_quality), AV_OPT_TYPE_INT, { 8 }, 0, 10, AE },
- { "frames_per_packet", "Number of frames to encode in each packet", OFFSET(frames_per_packet), AV_OPT_TYPE_INT, { 1 }, 1, 8, AE },
+ { "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 },
};
AVCodec ff_libspeex_encoder = {
.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,
+ .capabilities = AV_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 },
- .long_name = NULL_IF_CONFIG_SMALL("libspeex Speex"),
.priv_class = &class,
.defaults = defaults,
};
projects / ffmpeg / blobdiff