21af73eb21
Jean-Marc's original anti-collapse patch used a threshold on the
content of a decoded band to determine whether or not it should
be filled with random noise.
Since this is highly sensitive to the accuracy of the
implementation, it could lead to significant decoder output
differences even if decoding error up to that point was relatively
small.
This patch detects collapsed bands from the output of the vector
quantizer, using exact integer arithmetic.
It makes two simplifying assumptions:
a) If either input to haar1() is non-zero during TF resolution
adjustments, then the output will be non-zero.
b) If the content of a block is non-zero in any of the bands that
are used for folding, then the folded output will be non-zero.
b) in particular is likely to be false when SPREAD_NONE is used.
It also ignores the case where mid and side are orthogonal in
stereo_merge, but this is relatively unlikely.
This misses just over 3% of the cases that Jean-Marc's anti-collapse
detection strategy would catch, but does not mis-classify any (all
detected collapses are true collapses).
This patch overloads the "fill" parameter to mark which blocks have
non-zero content for folding.
As a consequence, if a set of blocks on one side of a split has
collapsed, _no_ folding is done: the result would be zero anyway,
except for short blocks with SPREAD_AGGRESSIVE that are split down
to a single block, but a) that means a lot of bits were available
so a collapse is unlikely and b) anti-collapse can fill the block
anyway, if it's used.
This also means that if itheta==0 or itheta==16384, we no longer
fold at all on that side (even with long blocks), since we'd be
multiplying the result by zero anyway.
73 lines
3.1 KiB
C
73 lines
3.1 KiB
C
/* Copyright (c) 2007-2008 CSIRO
|
|
Copyright (c) 2007-2009 Xiph.Org Foundation
|
|
Written by Jean-Marc Valin */
|
|
/**
|
|
@file vq.h
|
|
@brief Vector quantisation of the residual
|
|
*/
|
|
/*
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions
|
|
are met:
|
|
|
|
- Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
|
|
- Redistributions in binary form must reproduce the above copyright
|
|
notice, this list of conditions and the following disclaimer in the
|
|
documentation and/or other materials provided with the distribution.
|
|
|
|
- Neither the name of the Xiph.org Foundation nor the names of its
|
|
contributors may be used to endorse or promote products derived from
|
|
this software without specific prior written permission.
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR
|
|
CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
|
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
|
PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
|
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
|
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
|
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*/
|
|
|
|
#ifndef VQ_H
|
|
#define VQ_H
|
|
|
|
#include "entenc.h"
|
|
#include "entdec.h"
|
|
#include "modes.h"
|
|
|
|
/** Algebraic pulse-vector quantiser. The signal x is replaced by the sum of
|
|
* the pitch and a combination of pulses such that its norm is still equal
|
|
* to 1. This is the function that will typically require the most CPU.
|
|
* @param x Residual signal to quantise/encode (returns quantised version)
|
|
* @param W Perceptual weight to use when optimising (currently unused)
|
|
* @param N Number of samples to encode
|
|
* @param K Number of pulses to use
|
|
* @param p Pitch vector (it is assumed that p+x is a unit vector)
|
|
* @param enc Entropy encoder state
|
|
* @ret A mask indicating which blocks in the band received pulses
|
|
*/
|
|
unsigned alg_quant(celt_norm *X, int N, int K, int spread, int B, celt_norm *lowband,
|
|
int resynth, ec_enc *enc, celt_int32 *seed, celt_word16 gain);
|
|
|
|
/** Algebraic pulse decoder
|
|
* @param x Decoded normalised spectrum (returned)
|
|
* @param N Number of samples to decode
|
|
* @param K Number of pulses to use
|
|
* @param p Pitch vector (automatically added to x)
|
|
* @param dec Entropy decoder state
|
|
* @ret A mask indicating which blocks in the band received pulses
|
|
*/
|
|
unsigned alg_unquant(celt_norm *X, int N, int K, int spread, int B,
|
|
celt_norm *lowband, ec_dec *dec, celt_int32 *seed, celt_word16 gain);
|
|
|
|
void renormalise_vector(celt_norm *X, int N, celt_word16 gain);
|
|
|
|
int stereo_itheta(celt_norm *X, celt_norm *Y, int stereo, int N);
|
|
|
|
#endif /* VQ_H */
|