|
5
|
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 * $Id: echo.h,v 1.9 2006/10/24 13:45:28 steveu Exp $
|
|
|
28 */
|
|
|
29
|
|
|
30 /*! \file */
|
|
|
31
|
|
|
32 #if !defined(_ECHO_H_)
|
|
|
33 #define _ECHO_H_
|
|
|
34
|
|
|
35 /*! \page echo_can_page Line echo cancellation for voice
|
|
|
36
|
|
|
37 \section echo_can_page_sec_1 What does it do?
|
|
|
38 This module aims to provide G.168-2002 compliant echo cancellation, to remove
|
|
|
39 electrical echoes (e.g. from 2-4 wire hybrids) from voice calls.
|
|
|
40
|
|
|
41 \section echo_can_page_sec_2 How does it work?
|
|
|
42 The heart of the echo cancellor is FIR filter. This is adapted to match the echo
|
|
|
43 impulse response of the telephone line. It must be long enough to adequately cover
|
|
|
44 the duration of that impulse response. The signal transmitted to the telephone line
|
|
|
45 is passed through the FIR filter. Once the FIR is properly adapted, the resulting
|
|
|
46 output is an estimate of the echo signal received from the line. This is subtracted
|
|
|
47 from the received signal. The result is an estimate of the signal which originated
|
|
|
48 at the far end of the line, free from echos of our own transmitted signal.
|
|
|
49
|
|
|
50 The least mean squares (LMS) algorithm is attributed to Widrow and Hoff, and was
|
|
|
51 introduced in 1960. It is the commonest form of filter adaption used in things
|
|
|
52 like modem line equalisers and line echo cancellers. There it works very well.
|
|
|
53 However, it only works well for signals of constant amplitude. It works very poorly
|
|
|
54 for things like speech echo cancellation, where the signal level varies widely.
|
|
|
55 This is quite easy to fix. If the signal level is normalised - similar to applying
|
|
|
56 AGC - LMS can work as well for a signal of varying amplitude as it does for a modem
|
|
|
57 signal. This normalised least mean squares (NLMS) algorithm is the commonest one used
|
|
|
58 for speech echo cancellation. Many other algorithms exist - e.g. RLS (essentially
|
|
|
59 the same as Kalman filtering), FAP, etc. Some perform significantly better than NLMS.
|
|
|
60 However, factors such as computational complexity and patents favour the use of NLMS.
|
|
|
61
|
|
|
62 A simple refinement to NLMS can improve its performance with speech. NLMS tends
|
|
|
63 to adapt best to the strongest parts of a signal. If the signal is white noise,
|
|
|
64 the NLMS algorithm works very well. However, speech has more low frequency than
|
|
|
65 high frequency content. Pre-whitening (i.e. filtering the signal to flatten
|
|
|
66 its spectrum) the echo signal improves the adapt rate for speech, and ensures the
|
|
|
67 final residual signal is not heavily biased towards high frequencies. A very low
|
|
|
68 complexity filter is adequate for this, so pre-whitening adds little to the
|
|
|
69 compute requirements of the echo canceller.
|
|
|
70
|
|
|
71 An FIR filter adapted using pre-whitened NLMS performs well, provided certain
|
|
|
72 conditions are met:
|
|
|
73
|
|
|
74 - The transmitted signal has poor self-correlation.
|
|
|
75 - There is no signal being generated within the environment being cancelled.
|
|
|
76
|
|
|
77 The difficulty is that neither of these can be guaranteed.
|
|
|
78
|
|
|
79 If the adaption is performed while transmitting noise (or something fairly noise
|
|
|
80 like, such as voice) the adaption works very well. If the adaption is performed
|
|
|
81 while transmitting something highly correlative (typically narrow band energy
|
|
|
82 such as signalling tones or DTMF), the adaption can go seriously wrong. The reason
|
|
|
83 is there is only one solution for the adaption on a near random signal - the impulse
|
|
|
84 response of the line. For a repetitive signal, there are any number of solutions
|
|
|
85 which converge the adaption, and nothing guides the adaption to choose the generalised
|
|
|
86 one. Allowing an untrained canceller to converge on this kind of narrowband
|
|
|
87 energy probably a good thing, since at least it cancels the tones. Allowing a well
|
|
|
88 converged canceller to continue converging on such energy is just a way to ruin
|
|
|
89 its generalised adaption. A narrowband detector is needed, so adapation can be
|
|
|
90 suspended at appropriate times.
|
|
|
91
|
|
|
92 The adaption process is based on trying to eliminate the received signal. When
|
|
|
93 there is any signal from within the environment being cancelled it may upset the
|
|
|
94 adaption process. Similarly, if the signal we are transmitting is small, noise
|
|
|
95 may dominate and disturb the adaption process. If we can ensure that the
|
|
|
96 adaption is only performed when we are transmitting a significant signal level,
|
|
|
97 and the environment is not, things will be OK. Clearly, it is easy to tell when
|
|
|
98 we are sending a significant signal. Telling, if the environment is generating a
|
|
|
99 significant signal, and doing it with sufficient speed that the adaption will
|
|
|
100 not have diverged too much more we stop it, is a little harder.
|
|
|
101
|
|
|
102 The key problem in detecting when the environment is sourcing significant energy
|
|
|
103 is that we must do this very quickly. Given a reasonably long sample of the
|
|
|
104 received signal, there are a number of strategies which may be used to assess
|
|
|
105 whether that signal contains a strong far end component. However, by the time
|
|
|
106 that assessment is complete the far end signal will have already caused major
|
|
|
107 mis-convergence in the adaption process. An assessment algorithm is needed which
|
|
|
108 produces a fairly accurate result from a very short burst of far end energy.
|
|
|
109
|
|
|
110 \section echo_can_page_sec_3 How do I use it?
|
|
|
111 The echo cancellor processes both the transmit and receive streams sample by
|
|
|
112 sample. The processing function is not declared inline. Unfortunately,
|
|
|
113 cancellation requires many operations per sample, so the call overhead is only a
|
|
|
114 minor burden.
|
|
|
115 */
|
|
|
116
|
|
|
117 #include "fir.h"
|
|
|
118
|
|
|
119 /* Mask bits for the adaption mode */
|
|
|
120
|
|
|
121 #define ECHO_CAN_USE_ADAPTION 0x01
|
|
|
122 #define ECHO_CAN_USE_NLP 0x02
|
|
|
123 #define ECHO_CAN_USE_CNG 0x04
|
|
|
124 #define ECHO_CAN_USE_CLIP 0x08
|
|
|
125 #define ECHO_CAN_USE_TX_HPF 0x10
|
|
|
126 #define ECHO_CAN_USE_RX_HPF 0x20
|
|
|
127 #define ECHO_CAN_DISABLE 0x40
|
|
|
128
|
|
|
129 /*!
|
|
|
130 G.168 echo canceller descriptor. This defines the working state for a line
|
|
|
131 echo canceller.
|
|
|
132 */
|
|
|
133 typedef struct
|
|
|
134 {
|
|
|
135 int16_t tx,rx;
|
|
|
136 int16_t clean;
|
|
|
137 int16_t clean_nlp;
|
|
|
138
|
|
|
139 int nonupdate_dwell;
|
|
|
140 int curr_pos;
|
|
|
141 int taps;
|
|
|
142 int log2taps;
|
|
|
143 int adaption_mode;
|
|
|
144
|
|
|
145 int cond_met;
|
|
|
146 int32_t Pstates;
|
|
|
147 int16_t adapt;
|
|
|
148 int32_t factor;
|
|
|
149 int16_t shift;
|
|
|
150
|
|
|
151 /* Average levels and averaging filter states */
|
|
|
152 int Ltxacc, Lrxacc, Lcleanacc, Lclean_bgacc;
|
|
|
153 int Ltx, Lrx;
|
|
|
154 int Lclean;
|
|
|
155 int Lclean_bg;
|
|
|
156 int Lbgn, Lbgn_acc, Lbgn_upper, Lbgn_upper_acc;
|
|
|
157
|
|
|
158 /* foreground and background filter states */
|
|
|
159 fir16_state_t fir_state;
|
|
|
160 fir16_state_t fir_state_bg;
|
|
|
161 int16_t *fir_taps16[2];
|
|
|
162
|
|
|
163 /* DC blocking filter states */
|
|
|
164 int tx_1, tx_2, rx_1, rx_2;
|
|
|
165
|
|
|
166 /* optional High Pass Filter states */
|
|
|
167 int32_t xvtx[5], yvtx[5];
|
|
|
168 int32_t xvrx[5], yvrx[5];
|
|
|
169
|
|
|
170 /* Parameters for the optional Hoth noise generator */
|
|
|
171 int cng_level;
|
|
|
172 int cng_rndnum;
|
|
|
173 int cng_filter;
|
|
|
174
|
|
|
175 /* snapshot sample of coeffs used for development */
|
|
|
176 int16_t *snapshot;
|
|
|
177
|
|
|
178 } echo_can_state_t;
|
|
|
179
|
|
|
180 /*! Create a voice echo canceller context.
|
|
|
181 \param len The length of the canceller, in samples.
|
|
|
182 \return The new canceller context, or NULL if the canceller could not be created.
|
|
|
183 */
|
|
|
184 echo_can_state_t *echo_can_create(int len, int adaption_mode);
|
|
|
185
|
|
|
186 /*! Free a voice echo canceller context.
|
|
|
187 \param ec The echo canceller context.
|
|
|
188 */
|
|
|
189 void echo_can_free(echo_can_state_t *ec);
|
|
|
190
|
|
|
191 /*! Flush (reinitialise) a voice echo canceller context.
|
|
|
192 \param ec The echo canceller context.
|
|
|
193 */
|
|
|
194 void echo_can_flush(echo_can_state_t *ec);
|
|
|
195
|
|
|
196 /*! Set the adaption mode of a voice echo canceller context.
|
|
|
197 \param ec The echo canceller context.
|
|
|
198 \param adapt The mode.
|
|
|
199 */
|
|
|
200 void echo_can_adaption_mode(echo_can_state_t *ec, int adaption_mode);
|
|
|
201
|
|
|
202 void echo_can_snapshot(echo_can_state_t *ec);
|
|
|
203
|
|
|
204 /*! Process a sample through a voice echo canceller.
|
|
|
205 \param ec The echo canceller context.
|
|
|
206 \param tx The transmitted audio sample.
|
|
|
207 \param rx The received audio sample.
|
|
|
208 \return The clean (echo cancelled) received sample.
|
|
|
209 */
|
|
|
210 int16_t echo_can_update(echo_can_state_t *ec, int16_t tx, int16_t rx);
|
|
|
211
|
|
|
212 /*! Process to high pass filter the tx signal.
|
|
|
213 \param ec The echo canceller context.
|
|
|
214 \param tx The transmitted auio sample.
|
|
|
215 \return The HP filtered transmit sample, send this to your D/A.
|
|
|
216 */
|
|
|
217 int16_t echo_can_hpf_tx(echo_can_state_t *ec, int16_t tx);
|
|
|
218
|
|
|
219 #endif
|
|
|
220 /*- End of file ------------------------------------------------------------*/
|
