drivers/staging/echo/echo.h

   1 /*
   2  * SpanDSP - a series of DSP components for telephony
   3  *
   4  * echo.c - A line echo canceller.  This code is being developed
   5  *          against and partially complies with G168.
   6  *
   7  * Written by Steve Underwood <steveu@coppice.org>
   8  *         and David Rowe <david_at_rowetel_dot_com>
   9  *
  10  * Copyright (C) 2001 Steve Underwood and 2007 David Rowe
  11  *
  12  * All rights reserved.
  13  *
  14  * This program is free software; you can redistribute it and/or modify
  15  * it under the terms of the GNU General Public License version 2, as
  16  * published by the Free Software Foundation.
  17  *
  18  * This program is distributed in the hope that it will be useful,
  19  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  20  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  21  * GNU General Public License for more details.
  22  *
  23  * You should have received a copy of the GNU General Public License
  24  * along with this program; if not, write to the Free Software
  25  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  26  */
  27
  28 #ifndef __ECHO_H
  29 #define __ECHO_H
  30
  31 /*
  32 Line echo cancellation for voice
  33
  34 What does it do?
  35
  36 This module aims to provide G.168-2002 compliant echo cancellation, to remove
  37 electrical echoes (e.g. from 2-4 wire hybrids) from voice calls.
  38
  39 How does it work?
  40
  41 The heart of the echo cancellor is FIR filter. This is adapted to match the
  42 echo impulse response of the telephone line. It must be long enough to
  43 adequately cover the duration of that impulse response. The signal transmitted
  44 to the telephone line is passed through the FIR filter. Once the FIR is
  45 properly adapted, the resulting output is an estimate of the echo signal
  46 received from the line. This is subtracted from the received signal. The result
  47 is an estimate of the signal which originated at the far end of the line, free
  48 from echos of our own transmitted signal.
  49
  50 The least mean squares (LMS) algorithm is attributed to Widrow and Hoff, and
  51 was introduced in 1960. It is the commonest form of filter adaption used in
  52 things like modem line equalisers and line echo cancellers. There it works very
  53 well.  However, it only works well for signals of constant amplitude. It works
  54 very poorly for things like speech echo cancellation, where the signal level
  55 varies widely.  This is quite easy to fix. If the signal level is normalised -
  56 similar to applying AGC - LMS can work as well for a signal of varying
  57 amplitude as it does for a modem signal. This normalised least mean squares
  58 (NLMS) algorithm is the commonest one used for speech echo cancellation. Many
  59 other algorithms exist - e.g. RLS (essentially the same as Kalman filtering),
  60 FAP, etc. Some perform significantly better than NLMS.  However, factors such
  61 as computational complexity and patents favour the use of NLMS.
  62
  63 A simple refinement to NLMS can improve its performance with speech. NLMS tends
  64 to adapt best to the strongest parts of a signal. If the signal is white noise,
  65 the NLMS algorithm works very well. However, speech has more low frequency than
  66 high frequency content. Pre-whitening (i.e. filtering the signal to flatten its
  67 spectrum) the echo signal improves the adapt rate for speech, and ensures the
  68 final residual signal is not heavily biased towards high frequencies. A very
  69 low complexity filter is adequate for this, so pre-whitening adds little to the
  70 compute requirements of the echo canceller.
  71
  72 An FIR filter adapted using pre-whitened NLMS performs well, provided certain
  73 conditions are met:
  74
  75     - The transmitted signal has poor self-correlation.
  76     - There is no signal being generated within the environment being
  77       cancelled.
  78
  79 The difficulty is that neither of these can be guaranteed.
  80
  81 If the adaption is performed while transmitting noise (or something fairly
  82 noise like, such as voice) the adaption works very well. If the adaption is
  83 performed while transmitting something highly correlative (typically narrow
  84 band energy such as signalling tones or DTMF), the adaption can go seriously
  85 wrong. The reason is there is only one solution for the adaption on a near
  86 random signal - the impulse response of the line. For a repetitive signal,
  87 there are any number of solutions which converge the adaption, and nothing
  88 guides the adaption to choose the generalised one. Allowing an untrained
  89 canceller to converge on this kind of narrowband energy probably a good thing,
  90 since at least it cancels the tones. Allowing a well converged canceller to
  91 continue converging on such energy is just a way to ruin its generalised
  92 adaption. A narrowband detector is needed, so adapation can be suspended at
  93 appropriate times.
  94
  95 The adaption process is based on trying to eliminate the received signal. When
  96 there is any signal from within the environment being cancelled it may upset
  97 the adaption process. Similarly, if the signal we are transmitting is small,
  98 noise may dominate and disturb the adaption process. If we can ensure that the
  99 adaption is only performed when we are transmitting a significant signal level,
 100 and the environment is not, things will be OK. Clearly, it is easy to tell when
 101 we are sending a significant signal. Telling, if the environment is generating
 102 a significant signal, and doing it with sufficient speed that the adaption will
 103 not have diverged too much more we stop it, is a little harder.
 104
 105 The key problem in detecting when the environment is sourcing significant
 106 energy is that we must do this very quickly. Given a reasonably long sample of
 107 the received signal, there are a number of strategies which may be used to
 108 assess whether that signal contains a strong far end component. However, by the
 109 time that assessment is complete the far end signal will have already caused
 110 major mis-convergence in the adaption process. An assessment algorithm is
 111 needed which produces a fairly accurate result from a very short burst of far
 112 end energy.
 113
 114 How do I use it?
 115
 116 The echo cancellor processes both the transmit and receive streams sample by
 117 sample. The processing function is not declared inline. Unfortunately,
 118 cancellation requires many operations per sample, so the call overhead is only
 119 a minor burden.
 120 */
 121
 122 #include "fir.h"
 123 #include "oslec.h"
 124
 125 /*
 126     G.168 echo canceller descriptor. This defines the working state for a line
 127     echo canceller.
 128 */
 129 struct oslec_state {
 130         int16_t tx;
 131         int16_t rx;
 132         int16_t clean;
 133         int16_t clean_nlp;
 134
 135         int nonupdate_dwell;
 136         int curr_pos;
 137         int taps;
 138         int log2taps;
 139         int adaption_mode;
 140
 141         int cond_met;
 142         int32_t Pstates;
 143         int16_t adapt;
 144         int32_t factor;
 145         int16_t shift;
 146
 147         /* Average levels and averaging filter states */
 148         int Ltxacc;
 149         int Lrxacc;
 150         int Lcleanacc;
 151         int Lclean_bgacc;
 152         int Ltx;
 153         int Lrx;
 154         int Lclean;
 155         int Lclean_bg;
 156         int Lbgn;
 157         int Lbgn_acc;
 158         int Lbgn_upper;
 159         int Lbgn_upper_acc;
 160
 161         /* foreground and background filter states */
 162         struct fir16_state_t fir_state;
 163         struct fir16_state_t fir_state_bg;
 164         int16_t *fir_taps16[2];
 165
 166         /* DC blocking filter states */
 167         int tx_1;
 168         int tx_2;
 169         int rx_1;
 170         int rx_2;
 171
 172         /* optional High Pass Filter states */
 173         int32_t xvtx[5];
 174         int32_t yvtx[5];
 175         int32_t xvrx[5];
 176         int32_t yvrx[5];
 177
 178         /* Parameters for the optional Hoth noise generator */
 179         int cng_level;
 180         int cng_rndnum;
 181         int cng_filter;
 182
 183         /* snapshot sample of coeffs used for development */
 184         int16_t *snapshot;
 185 };
 186
 187 #endif /* __ECHO_H */