aacenc: add support for encoding files using Long Term Prediction

Long Term Prediction allows for prediction of spectral coefficients
via the previously decoded time-dependent samples. This feature
works well with harmonic content 2 or more frames long, like speech,
human or non-human, piano music or any constant tones at very low
bitrates.

It should be noted that the current coder is highly efficient and
the rate control system is unable to encode files at extremely
low bitrates (less than 14kbps seems to be impossible) so this
extension isn't capable of optimum operation. Dramatic difference
is observable with some types of audio and speech but for the most
part the audiable differences are subtle. The spectrum looks better
however so the encoder is able to harvest the additional bits that
this feature provies, should the user choose to enable it. So
it's best to enable this feature only if encoding at the absolutely
lowest bitrate that the encoder is capable of.

1 files changed, 2 insertions, 0 deletions

diff --git a/libavcodec/aac.h b/libavcodec/aac.h
index 37f98adb31..3333bfe5b2 100644
--- a/libavcodec/aac.h
+++ b/libavcodec/aac.h
@@ -161,6 +161,7 @@ typedef struct PredictorState {
 typedef struct LongTermPrediction {
     int8_t present;
     int16_t lag;
+    int coef_idx;
     INTFLOAT coef;
     int8_t used[MAX_LTP_LONG_SFB];
 } LongTermPrediction;
@@ -260,6 +261,7 @@ typedef struct SingleChannelElement {
     DECLARE_ALIGNED(32, INTFLOAT, saved)[1536];     ///< overlap
     DECLARE_ALIGNED(32, INTFLOAT, ret_buf)[2048];   ///< PCM output buffer
     DECLARE_ALIGNED(16, INTFLOAT, ltp_state)[3072]; ///< time signal for LTP
+    DECLARE_ALIGNED(32, AAC_FLOAT, lcoeffs)[1024];  ///< MDCT of LTP coefficients (used by encoder)
     DECLARE_ALIGNED(32, AAC_FLOAT, prcoeffs)[1024]; ///< Main prediction coefs (used by encoder)
     PredictorState predictor_state[MAX_PREDICTORS];
     INTFLOAT *ret;                                  ///< PCM output