Merge commit '378a6315b7c48195ffd94e6aa9aa6d663d42b35e'

[ffmpeg] / libavcodec / libspeexenc.c

diff --git a/libavcodec/libspeexenc.c b/libavcodec/libspeexenc.c
index 7c93a32a2b8d953e2a3cd5df219695c1fa3f6500..e3db143f75c3a3641eb0a8f65d528921f014b426 100644 (file)
--- a/libavcodec/libspeexenc.c
+++ b/libavcodec/libspeexenc.c
@@ -62,6 +62,23 @@
  *     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>
@@ -75,7 +92,7 @@
 #include "internal.h"
 #include "audio_frame_queue.h"
 
-/* TODO: Think about converting abr, vad, dtx (still to come) and such flags to a bit field */
+/* TODO: Think about converting abr, vad, dtx and such flags to a bit field */
 typedef struct {
     AVClass *class;             ///< AVClass for private options
     SpeexBits bits;             ///< libspeex bitwriter context
@@ -86,6 +103,7 @@ typedef struct {
     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;
@@ -121,6 +139,7 @@ static av_cold void print_enc_params(AVCodecContext *avctx,
     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)
@@ -197,6 +216,13 @@ static av_cold int encode_init(AVCodecContext *avctx)
     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);
@@ -317,6 +343,7 @@ static const AVOption options[] = {
     { "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 },
 };