drivers/misc/echo/echo.h

   1 /* SPDX-License-Identifier: GPL-2.0-only */
   2 /*
   3  * SpanDSP - a series of DSP components for telephony
   4  *
   5  * echo.c - A line echo canceller.  This code is being developed
   6  *          against and partially complies with G168.
   7  *
   8  * Written by Steve Underwood <steveu@coppice.org>
   9  *         and David Rowe <david_at_rowetel_dot_com>
  10  *
  11  * Copyright (C) 2001 Steve Underwood and 2007 David Rowe
  12  *
  13  * All rights reserved.
  14  */
  15
  16 #ifndef __ECHO_H
  17 #define __ECHO_H
  18
  19 /*
  20 Line echo cancellation for voice
  21
  22 What does it do?
  23
  24 This module aims to provide G.168-2002 compliant echo cancellation, to remove
  25 electrical echoes (e.g. from 2-4 wire hybrids) from voice calls.
  26
  27 How does it work?
  28
  29 The heart of the echo cancellor is FIR filter. This is adapted to match the
  30 echo impulse response of the telephone line. It must be long enough to
  31 adequately cover the duration of that impulse response. The signal transmitted
  32 to the telephone line is passed through the FIR filter. Once the FIR is
  33 properly adapted, the resulting output is an estimate of the echo signal
  34 received from the line. This is subtracted from the received signal. The result
  35 is an estimate of the signal which originated at the far end of the line, free
  36 from echos of our own transmitted signal.
  37
  38 The least mean squares (LMS) algorithm is attributed to Widrow and Hoff, and
  39 was introduced in 1960. It is the commonest form of filter adaption used in
  40 things like modem line equalisers and line echo cancellers. There it works very
  41 well.  However, it only works well for signals of constant amplitude. It works
  42 very poorly for things like speech echo cancellation, where the signal level
  43 varies widely.  This is quite easy to fix. If the signal level is normalised -
  44 similar to applying AGC - LMS can work as well for a signal of varying
  45 amplitude as it does for a modem signal. This normalised least mean squares
  46 (NLMS) algorithm is the commonest one used for speech echo cancellation. Many
  47 other algorithms exist - e.g. RLS (essentially the same as Kalman filtering),
  48 FAP, etc. Some perform significantly better than NLMS.  However, factors such
  49 as computational complexity and patents favour the use of NLMS.
  50
  51 A simple refinement to NLMS can improve its performance with speech. NLMS tends
  52 to adapt best to the strongest parts of a signal. If the signal is white noise,
  53 the NLMS algorithm works very well. However, speech has more low frequency than
  54 high frequency content. Pre-whitening (i.e. filtering the signal to flatten its
  55 spectrum) the echo signal improves the adapt rate for speech, and ensures the
  56 final residual signal is not heavily biased towards high frequencies. A very
  57 low complexity filter is adequate for this, so pre-whitening adds little to the
  58 compute requirements of the echo canceller.
  59
  60 An FIR filter adapted using pre-whitened NLMS performs well, provided certain
  61 conditions are met:
  62
  63     - The transmitted signal has poor self-correlation.
  64     - There is no signal being generated within the environment being
  65       cancelled.
  66
  67 The difficulty is that neither of these can be guaranteed.
  68
  69 If the adaption is performed while transmitting noise (or something fairly
  70 noise like, such as voice) the adaption works very well. If the adaption is
  71 performed while transmitting something highly correlative (typically narrow
  72 band energy such as signalling tones or DTMF), the adaption can go seriously
  73 wrong. The reason is there is only one solution for the adaption on a near
  74 random signal - the impulse response of the line. For a repetitive signal,
  75 there are any number of solutions which converge the adaption, and nothing
  76 guides the adaption to choose the generalised one. Allowing an untrained
  77 canceller to converge on this kind of narrowband energy probably a good thing,
  78 since at least it cancels the tones. Allowing a well converged canceller to
  79 continue converging on such energy is just a way to ruin its generalised
  80 adaption. A narrowband detector is needed, so adapation can be suspended at
  81 appropriate times.
  82
  83 The adaption process is based on trying to eliminate the received signal. When
  84 there is any signal from within the environment being cancelled it may upset
  85 the adaption process. Similarly, if the signal we are transmitting is small,
  86 noise may dominate and disturb the adaption process. If we can ensure that the
  87 adaption is only performed when we are transmitting a significant signal level,
  88 and the environment is not, things will be OK. Clearly, it is easy to tell when
  89 we are sending a significant signal. Telling, if the environment is generating
  90 a significant signal, and doing it with sufficient speed that the adaption will
  91 not have diverged too much more we stop it, is a little harder.
  92
  93 The key problem in detecting when the environment is sourcing significant
  94 energy is that we must do this very quickly. Given a reasonably long sample of
  95 the received signal, there are a number of strategies which may be used to
  96 assess whether that signal contains a strong far end component. However, by the
  97 time that assessment is complete the far end signal will have already caused
  98 major mis-convergence in the adaption process. An assessment algorithm is
  99 needed which produces a fairly accurate result from a very short burst of far
 100 end energy.
 101
 102 How do I use it?
 103
 104 The echo cancellor processes both the transmit and receive streams sample by
 105 sample. The processing function is not declared inline. Unfortunately,
 106 cancellation requires many operations per sample, so the call overhead is only
 107 a minor burden.
 108 */
 109
 110 #include "fir.h"
 111 #include "oslec.h"
 112
 113 /*
 114     G.168 echo canceller descriptor. This defines the working state for a line
 115     echo canceller.
 116 */
 117 struct oslec_state {
 118         int16_t tx;
 119         int16_t rx;
 120         int16_t clean;
 121         int16_t clean_nlp;
 122
 123         int nonupdate_dwell;
 124         int curr_pos;
 125         int taps;
 126         int log2taps;
 127         int adaption_mode;
 128
 129         int cond_met;
 130         int32_t pstates;
 131         int16_t adapt;
 132         int32_t factor;
 133         int16_t shift;
 134
 135         /* Average levels and averaging filter states */
 136         int ltxacc;
 137         int lrxacc;
 138         int lcleanacc;
 139         int lclean_bgacc;
 140         int ltx;
 141         int lrx;
 142         int lclean;
 143         int lclean_bg;
 144         int lbgn;
 145         int lbgn_acc;
 146         int lbgn_upper;
 147         int lbgn_upper_acc;
 148
 149         /* foreground and background filter states */
 150         struct fir16_state_t fir_state;
 151         struct fir16_state_t fir_state_bg;
 152         int16_t *fir_taps16[2];
 153
 154         /* DC blocking filter states */
 155         int tx_1;
 156         int tx_2;
 157         int rx_1;
 158         int rx_2;
 159
 160         /* optional High Pass Filter states */
 161         int32_t xvtx[5];
 162         int32_t yvtx[5];
 163         int32_t xvrx[5];
 164         int32_t yvrx[5];
 165
 166         /* Parameters for the optional Hoth noise generator */
 167         int cng_level;
 168         int cng_rndnum;
 169         int cng_filter;
 170
 171         /* snapshot sample of coeffs used for development */
 172         int16_t *snapshot;
 173 };
 174
 175 #endif /* __ECHO_H */