1 #ifndef _RESAMPLING_QUEUE_H
2 #define _RESAMPLING_QUEUE_H 1
4 // Takes in samples from an input source, possibly with jitter, and outputs a fixed number
5 // of samples every iteration. Used to a) change sample rates if needed, and b) deal with
6 // input sources that don't have audio locked to video. For every input video
7 // frame, you call add_input_samples() with the received time point of the video frame,
8 // taken to be the _end_ point of the frame's audio. When you want to _output_ a finished
9 // frame with audio, you get_output_samples() with the number of samples you want, and will
10 // get exactly that number of samples back. If the input and output clocks are not in sync,
11 // the audio will be stretched for you. (If they are _very_ out of sync, this will come through
12 // as a pitch shift.) Of course, the process introduces some delay; you specify a target delay
13 // (typically measured in milliseconds, although more is fine) and the algorithm works to
14 // provide exactly that.
16 // A/V sync is a much harder problem than one would intuitively assume. This implementation
17 // is based on a 2012 paper by Fons Adriaensen, “Controlling adaptive resampling”
18 // (http://kokkinizita.linuxaudio.org/papers/adapt-resamp.pdf). The paper gives an algorithm
19 // that converges to jitter of <100 ns; the basic idea is to measure the _rate_ the input
20 // queue fills and is drained (as opposed to the length of the queue itself), and smoothly
21 // adjust the resampling rate so that it reaches steady state at the desired delay.
23 // Parts of the code is adapted from Adriaensen's project Zita-ajbridge (based on the same
24 // algorithm), although it has been heavily reworked for this use case. Original copyright follows:
26 // Copyright (C) 2012-2015 Fons Adriaensen <fons@linuxaudio.org>
28 // This program is free software; you can redistribute it and/or modify
29 // it under the terms of the GNU General Public License as published by
30 // the Free Software Foundation; either version 3 of the License, or
31 // (at your option) any later version.
33 // This program is distributed in the hope that it will be useful,
34 // but WITHOUT ANY WARRANTY; without even the implied warranty of
35 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
36 // GNU General Public License for more details.
38 // You should have received a copy of the GNU General Public License
39 // along with this program. If not, see <http://www.gnu.org/licenses/>.
41 #include <sys/types.h>
42 #include <zita-resampler/vresampler.h>
49 class ResamplingQueue {
51 // card_num is for debugging outputs only.
52 ResamplingQueue(unsigned card_num, unsigned freq_in, unsigned freq_out, unsigned num_channels, double expected_delay_seconds);
54 // If policy is DO_NOT_ADJUST_RATE, the resampling rate will not be changed.
55 // This is primarily useful if you have an extraordinary situation, such as
57 enum RateAdjustmentPolicy {
62 void add_input_samples(std::chrono::steady_clock::time_point ts, const float *samples, ssize_t num_samples, RateAdjustmentPolicy rate_adjustment_policy);
63 // Returns false if underrun.
64 bool get_output_samples(std::chrono::steady_clock::time_point ts, float *samples, ssize_t num_samples, RateAdjustmentPolicy rate_adjustment_policy);
67 void init_loop_filter(double bandwidth_hz);
69 VResampler vresampler;
72 unsigned freq_in, freq_out, num_channels;
74 bool first_output = true;
77 // Equivalent to t_a0 or t_a1 in the paper.
78 std::chrono::steady_clock::time_point ts;
80 // Number of samples that have been written to the queue (in total)
81 // at this time point. Equivalent to k_a0 or k_a1 in the paper.
82 size_t input_samples_received = 0;
84 // Set to false if we should not use the timestamp from this sample
85 // (e.g. if it is from a dropped frame and thus bad). In particular,
86 // we will not use it for updateing current_estimated_freq_in.
87 bool good_sample = false;
91 // The current rate at which we seem to get input samples, in Hz.
92 // For an ideal input, identical to freq_in.
93 double current_estimated_freq_in;
95 ssize_t total_consumed_samples = 0;
97 // Filter state for the loop filter.
98 double z1 = 0.0, z2 = 0.0, z3 = 0.0;
100 // Ratio between the two frequencies.
103 // Current correction ratio. ratio * rcorr gives the true ratio,
104 // so values above 1.0 means to pitch down (consume input samples slower).
107 // How much delay we are expected to have, in input samples.
108 // If actual delay drifts too much away from this, we will start
109 // changing the resampling ratio to compensate.
110 const double expected_delay;
112 // Input samples not yet fed into the resampler.
113 // TODO: Use a circular buffer instead, for efficiency.
114 std::deque<float> buffer;
117 #endif // !defined(_RESAMPLING_QUEUE_H)