+// Copyright Steinar H. Gunderson <sgunderson@bigfoot.com>
+// Licensed under the GPL, v2. (See the file COPYING.)
+
#include <stdio.h>
#include <string.h>
#include <math.h>
#include "interpolate.h"
#include "level.h"
#include "tap.h"
+#include "filter.h"
#define BUFSIZE 4096
#define C64_FREQUENCY 985248
#define GAMMA 0.166
#define ALPHA 1.0
-static float hysteresis_limit = 3000.0 / 32768.0;
+static float hysteresis_upper_limit = 3000.0 / 32768.0;
+static float hysteresis_lower_limit = -3000.0 / 32768.0;
static bool do_calibrate = true;
static bool output_cycles_plot = false;
-static bool use_filter = false;
static bool do_crop = false;
static float crop_start = 0.0f, crop_end = HUGE_VAL;
+
+static bool use_fir_filter = false;
static float filter_coeff[NUM_FILTER_COEFF] = { 1.0f }; // The rest is filled with 0.
+static bool use_rc_filter = false;
+static float rc_filter_freq;
static bool output_filtered = false;
+
static bool quiet = false;
static bool do_auto_level = false;
static bool output_leveled = false;
static std::vector<float> train_snap_points;
static bool do_train = false;
+// The frequency to filter on (for do_auto_level), in Hertz.
+// Larger values makes the compressor react faster, but if it is too large,
+// you'll ruin the waveforms themselves.
+static float auto_level_freq = 200.0;
+
// The minimum estimated sound level (for do_auto_level) at any given point.
// If you decrease this, you'll be able to amplify really silent signals
// by more, but you'll also increase the level of silent (ie. noise-only) segments,
// possibly caused misdetected pulses in these segments.
static float min_level = 0.05f;
-// between [x,x+1]
-double find_zerocrossing(const std::vector<float> &pcm, int x)
+// search for the value <limit> between [x,x+1]
+double find_crossing(const std::vector<float> &pcm, int x, float limit)
{
- if (pcm[x] == 0) {
- return x;
- }
- if (pcm[x + 1] == 0) {
- return x + 1;
- }
-
- assert(pcm[x + 1] < 0);
- assert(pcm[x] > 0);
-
double upper = x;
double lower = x + 1;
while (lower - upper > 1e-3) {
double mid = 0.5f * (upper + lower);
- if (lanczos_interpolate(pcm, mid) > 0) {
+ if (lanczos_interpolate(pcm, mid) > limit) {
upper = mid;
} else {
lower = mid;
static struct option long_options[] = {
{"auto-level", 0, 0, 'a' },
+ {"auto-level-freq", required_argument, 0, 'b' },
{"output-leveled", 0, 0, 'A' },
+ {"min-level", required_argument, 0, 'm' },
{"no-calibrate", 0, 0, 's' },
{"plot-cycles", 0, 0, 'p' },
{"hysteresis-limit", required_argument, 0, 'l' },
{"filter", required_argument, 0, 'f' },
+ {"rc-filter", required_argument, 0, 'r' },
{"output-filtered", 0, 0, 'F' },
{"crop", required_argument, 0, 'c' },
{"quiet", 0, 0, 'q' },
fprintf(stderr, "decode [OPTIONS] AUDIO-FILE > TAP-FILE\n");
fprintf(stderr, "\n");
fprintf(stderr, " -a, --auto-level automatically adjust amplitude levels throughout the file\n");
+ fprintf(stderr, " -b, --auto-level-freq minimum frequency in Hertz of corrected level changes (default 200 Hz)\n");
fprintf(stderr, " -A, --output-leveled output leveled waveform to leveled.raw\n");
fprintf(stderr, " -m, --min-level minimum estimated sound level (0..32768) for --auto-level\n");
fprintf(stderr, " -s, --no-calibrate do not try to calibrate on sync pulse length\n");
fprintf(stderr, " -p, --plot-cycles output debugging info to cycles.plot\n");
fprintf(stderr, " -l, --hysteresis-limit VAL change amplitude threshold for ignoring pulses (0..32768)\n");
fprintf(stderr, " -f, --filter C1:C2:C3:... specify FIR filter (up to %d coefficients)\n", NUM_FILTER_COEFF);
+ fprintf(stderr, " -r, --rc-filter FREQ send signal through a highpass RC filter with given frequency (in Hertz)\n");
fprintf(stderr, " -F, --output-filtered output filtered waveform to filtered.raw\n");
fprintf(stderr, " -c, --crop START[:END] use only the given part of the file\n");
fprintf(stderr, " -t, --train LEN1:LEN2:... train a filter for detecting any of the given number of cycles\n");
{
for ( ;; ) {
int option_index = 0;
- int c = getopt_long(argc, argv, "aAm:spl:f:Fc:t:qh", long_options, &option_index);
+ int c = getopt_long(argc, argv, "ab:Am:spl:f:r:Fc:t:qh", long_options, &option_index);
if (c == -1)
break;
do_auto_level = true;
break;
+ case 'b':
+ auto_level_freq = atof(optarg);
+ break;
+
case 'A':
output_leveled = true;
break;
output_cycles_plot = true;
break;
- case 'l':
- hysteresis_limit = atof(optarg) / 32768.0;
+ case 'l': {
+ const char *hyststr = strtok(optarg, ": ");
+ hysteresis_upper_limit = atof(hyststr) / 32768.0;
+ hyststr = strtok(NULL, ": ");
+ if (hyststr == NULL) {
+ hysteresis_lower_limit = -hysteresis_upper_limit;
+ } else {
+ hysteresis_lower_limit = atof(hyststr) / 32768.0;
+ }
break;
+ }
case 'f': {
const char *coeffstr = strtok(optarg, ": ");
filter_coeff[coeff_index++] = atof(coeffstr);
coeffstr = strtok(NULL, ": ");
}
- use_filter = true;
+ use_fir_filter = true;
break;
}
+ case 'r':
+ use_rc_filter = true;
+ rc_filter_freq = atof(optarg);
+ break;
+
case 'F':
output_filtered = true;
break;
}
// TODO: Support AVX here.
-std::vector<float> do_filter(const std::vector<float>& pcm, const float* filter)
+std::vector<float> do_fir_filter(const std::vector<float>& pcm, const float* filter)
{
std::vector<float> filtered_pcm;
filtered_pcm.reserve(pcm.size());
return filtered_pcm;
}
+std::vector<float> do_rc_filter(const std::vector<float>& pcm, float freq, int sample_rate)
+{
+ // This is only a 6 dB/oct filter, which seemingly works better
+ // than the Filter class, which is a standard biquad (12 dB/oct).
+ // The b/c calculations come from libnyquist (atone.c);
+ // I haven't checked, but I suppose they fall out of the bilinear
+ // transform of the transfer function H(s) = s/(s + w).
+ std::vector<float> filtered_pcm;
+ filtered_pcm.resize(pcm.size());
+ const float b = 2.0f - cos(2.0 * M_PI * freq / sample_rate);
+ const float c = b - sqrt(b * b - 1.0f);
+ float prev_in = 0.0f;
+ float prev_out = 0.0f;
+ for (unsigned i = 0; i < pcm.size(); ++i) {
+ float in = pcm[i];
+ float out = c * (prev_out + in - prev_in);
+ filtered_pcm[i] = out;
+ prev_in = in;
+ prev_out = out;
+ }
+
+ if (output_filtered) {
+ FILE *fp = fopen("filtered.raw", "wb");
+ fwrite(filtered_pcm.data(), filtered_pcm.size() * sizeof(filtered_pcm[0]), 1, fp);
+ fclose(fp);
+ }
+
+ return filtered_pcm;
+}
+
std::vector<pulse> detect_pulses(const std::vector<float> &pcm, int sample_rate)
{
std::vector<pulse> pulses;
// Find the flanks.
- int last_bit = -1;
+ enum State { START, ABOVE, BELOW } state = START;
double last_downflank = -1;
for (unsigned i = 0; i < pcm.size(); ++i) {
- int bit = (pcm[i] > 0) ? 1 : 0;
- if (bit == 0 && last_bit == 1) {
- // Check if we ever go up above <hysteresis_limit> before we dip down again.
- bool true_pulse = false;
- unsigned j;
- int min_level_after = 32767;
- for (j = i; j < pcm.size(); ++j) {
- min_level_after = std::min<int>(min_level_after, pcm[j]);
- if (pcm[j] > 0) break;
- if (pcm[j] < -hysteresis_limit) {
- true_pulse = true;
- break;
+ if (pcm[i] > hysteresis_upper_limit) {
+ state = ABOVE;
+ } else if (pcm[i] < hysteresis_lower_limit) {
+ if (state == ABOVE) {
+ // down-flank!
+ double t = find_crossing(pcm, i - 1, hysteresis_lower_limit) * (1.0 / sample_rate) + crop_start;
+ if (last_downflank > 0) {
+ pulse p;
+ p.time = t;
+ p.len = t - last_downflank;
+ pulses.push_back(p);
}
+ last_downflank = t;
}
-
- if (!true_pulse) {
-#if 0
- fprintf(stderr, "Ignored down-flank at %.6f seconds due to hysteresis (%d < %d).\n",
- double(i) / sample_rate, -min_level_after, hysteresis_limit);
-#endif
- i = j;
- continue;
- }
-
- // down-flank!
- double t = find_zerocrossing(pcm, i - 1) * (1.0 / sample_rate) + crop_start;
- if (last_downflank > 0) {
- pulse p;
- p.time = t;
- p.len = t - last_downflank;
- pulses.push_back(p);
- }
- last_downflank = t;
+ state = BELOW;
}
- last_bit = bit;
}
return pulses;
}
fclose(fp);
}
+std::pair<int, double> find_closest_point(double x, const std::vector<float> &points)
+{
+ int best_point = 0;
+ double best_dist = (x - points[0]) * (x - points[0]);
+ for (unsigned j = 1; j < train_snap_points.size(); ++j) {
+ double dist = (x - points[j]) * (x - points[j]);
+ if (dist < best_dist) {
+ best_point = j;
+ best_dist = dist;
+ }
+ }
+ return std::make_pair(best_point, best_dist);
+}
+
float eval_badness(const std::vector<pulse>& pulses, double calibration_factor)
{
double sum_badness = 0.0;
for (unsigned i = 0; i < pulses.size(); ++i) {
double cycles = pulses[i].len * calibration_factor * C64_FREQUENCY;
if (cycles > 2000.0) cycles = 2000.0; // Don't make pauses arbitrarily bad.
- double badness = (cycles - train_snap_points[0]) * (cycles - train_snap_points[0]);
- for (unsigned j = 1; j < train_snap_points.size(); ++j) {
- badness = std::min(badness, (cycles - train_snap_points[j]) * (cycles - train_snap_points[j]));
- }
- sum_badness += badness;
+ std::pair<int, double> selected_point_and_sq_dist = find_closest_point(cycles, train_snap_points);
+ sum_badness += selected_point_and_sq_dist.second;
}
return sqrt(sum_badness / (pulses.size() - 1));
}
-void spsa_train(std::vector<float> &pcm, int sample_rate)
+void find_kmeans(const std::vector<pulse> &pulses, double calibration_factor, const std::vector<float> &initial_centers)
+{
+ std::vector<float> last_centers = initial_centers;
+ std::vector<float> sums;
+ std::vector<float> num;
+ sums.resize(initial_centers.size());
+ num.resize(initial_centers.size());
+ for ( ;; ) {
+ for (unsigned i = 0; i < initial_centers.size(); ++i) {
+ sums[i] = 0.0f;
+ num[i] = 0;
+ }
+ for (unsigned i = 0; i < pulses.size(); ++i) {
+ double cycles = pulses[i].len * calibration_factor * C64_FREQUENCY;
+ // Ignore heavy outliers, which are almost always long pauses.
+ if (cycles > 2000.0) {
+ continue;
+ }
+ std::pair<int, double> selected_point_and_sq_dist = find_closest_point(cycles, last_centers);
+ int p = selected_point_and_sq_dist.first;
+ sums[p] += cycles;
+ ++num[p];
+ }
+ bool any_moved = false;
+ for (unsigned i = 0; i < initial_centers.size(); ++i) {
+ if (num[i] == 0) {
+ fprintf(stderr, "K-means broke down, can't output new reference training points\n");
+ return;
+ }
+ float new_center = sums[i] / num[i];
+ if (fabs(new_center - last_centers[i]) > 1e-3) {
+ any_moved = true;
+ }
+ last_centers[i] = new_center;
+ }
+ if (!any_moved) {
+ break;
+ }
+ }
+ fprintf(stderr, "New reference training points:");
+ for (unsigned i = 0; i < last_centers.size(); ++i) {
+ fprintf(stderr, " %.3f", last_centers[i]);
+ }
+ fprintf(stderr, "\n");
+}
+
+void spsa_train(const std::vector<float> &pcm, int sample_rate)
{
- // Train!
float filter[NUM_FILTER_COEFF] = { 1.0f }; // The rest is filled with 0.
float start_c = INITIAL_C;
filter2[i] = std::max(std::min(filter[i] + c * p[i], 1.0f), -1.0f);
}
- std::vector<pulse> pulses1 = detect_pulses(do_filter(pcm, filter1), sample_rate);
- std::vector<pulse> pulses2 = detect_pulses(do_filter(pcm, filter2), sample_rate);
+ std::vector<pulse> pulses1 = detect_pulses(do_fir_filter(pcm, filter1), sample_rate);
+ std::vector<pulse> pulses2 = detect_pulses(do_fir_filter(pcm, filter2), sample_rate);
float badness1 = eval_badness(pulses1, 1.0);
float badness2 = eval_badness(pulses2, 1.0);
best_badness = badness1;
printf("\n");
+ find_kmeans(pulses1, 1.0, train_snap_points);
+
if (output_cycles_plot) {
output_cycle_plot(pulses1, 1.0);
}
pcm = crop(pcm, crop_start, crop_end, sample_rate);
}
- if (use_filter) {
- pcm = do_filter(pcm, filter_coeff);
+ if (use_fir_filter) {
+ pcm = do_fir_filter(pcm, filter_coeff);
+ }
+
+ if (use_rc_filter) {
+ pcm = do_rc_filter(pcm, rc_filter_freq, sample_rate);
}
if (do_auto_level) {
- pcm = level_samples(pcm, min_level, sample_rate);
+ pcm = level_samples(pcm, min_level, auto_level_freq, sample_rate);
if (output_leveled) {
FILE *fp = fopen("leveled.raw", "wb");
fwrite(pcm.data(), pcm.size() * sizeof(pcm[0]), 1, fp);
projects / c64tapwav / blobdiff