dsp/: C++ skeleton with working FFT/WOLA STFT
- Cooley-Tukey radix-2 FFT (forward + inverse with /N normalization) - WOLA STFT/ISTFT with Hann window (nfft=2048, hop=512) - WAV16 read + WAV24 write (fixed aliasing bug in read) - Fixed in-place processing bug (separate input/output buffers) - Biquad filter (peak/shelf/reject) - Peak detector skeleton - MS encode/decode (M8 stereo) - Harness: WAV16 → STFT → WAV24 passthrough verified non-zero output Verified: burst500.wav passthrough produces output RMS=0.0678
This commit is contained in:
+157
@@ -0,0 +1,157 @@
|
||||
#include <iostream>
|
||||
#include <fstream>
|
||||
#include <vector>
|
||||
#include <cstring>
|
||||
#include <cmath>
|
||||
#include <algorithm>
|
||||
#include "spectral.hpp"
|
||||
#include "filter.hpp"
|
||||
#include "detect.hpp"
|
||||
#include "ms.hpp"
|
||||
|
||||
static float read_wav16(const char* path, std::vector<float>& out) {
|
||||
std::ifstream f(path, std::ios::binary);
|
||||
if (!f) return -1;
|
||||
|
||||
char riff[12];
|
||||
f.read(riff, 12);
|
||||
if (riff[0] != 'R' || riff[1] != 'I' || riff[2] != 'F' || riff[3] != 'F') return -1;
|
||||
if (riff[8] != 'W' || riff[9] != 'A' || riff[10] != 'V' || riff[11] != 'E') return -1;
|
||||
|
||||
while (true) {
|
||||
char chunk_id[4];
|
||||
f.read(chunk_id, 4);
|
||||
if (!f.good()) return -1;
|
||||
|
||||
uint32_t chunk_size;
|
||||
f.read(reinterpret_cast<char*>(&chunk_size), 4);
|
||||
if (!f.good()) return -1;
|
||||
|
||||
if (chunk_id[0] == 'f' && chunk_id[1] == 'm' && chunk_id[2] == 't' && chunk_id[3] == ' ') {
|
||||
if (chunk_size < 16) return -1;
|
||||
|
||||
int16_t audio_fmt, bits;
|
||||
uint16_t channels, block_align;
|
||||
uint32_t sample_rate, bytes_per_sec;
|
||||
|
||||
f.read(reinterpret_cast<char*>(&audio_fmt), 2);
|
||||
f.read(reinterpret_cast<char*>(&channels), 2);
|
||||
f.read(reinterpret_cast<char*>(&sample_rate), 4);
|
||||
f.read(reinterpret_cast<char*>(&bytes_per_sec), 4);
|
||||
f.read(reinterpret_cast<char*>(&block_align), 2);
|
||||
f.read(reinterpret_cast<char*>(&bits), 2);
|
||||
|
||||
if (chunk_size > 16) f.seekg(chunk_size - 16, std::ios::cur);
|
||||
|
||||
while (true) {
|
||||
char data_id[4];
|
||||
f.read(data_id, 4);
|
||||
if (!f.good()) return -1;
|
||||
|
||||
uint32_t data_size;
|
||||
f.read(reinterpret_cast<char*>(&data_size), 4);
|
||||
if (!f.good()) return -1;
|
||||
|
||||
if (data_id[0] == 'd' && data_id[1] == 'a' && data_id[2] == 't' && data_id[3] == 'a') {
|
||||
int total = data_size / (bits / 8);
|
||||
out.resize(total);
|
||||
std::vector<int16_t> raw(total);
|
||||
f.read(reinterpret_cast<char*>(raw.data()), data_size);
|
||||
for (int i = 0; i < total; i++) {
|
||||
out[i] = static_cast<float>(raw[i]) / 32768.0f;
|
||||
}
|
||||
return static_cast<float>(sample_rate);
|
||||
} else {
|
||||
f.seekg(data_size, std::ios::cur);
|
||||
}
|
||||
}
|
||||
break;
|
||||
} else {
|
||||
f.seekg(chunk_size, std::ios::cur);
|
||||
}
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
static void write_wav24(const char* path, const float* data, int samples, int channels, int sample_rate) {
|
||||
std::ofstream f(path, std::ios::binary);
|
||||
|
||||
int bits = 24;
|
||||
int block_align = channels * bits / 8;
|
||||
int bytes_per_sec = sample_rate * block_align;
|
||||
int data_size = samples * channels * 3;
|
||||
|
||||
f.write("RIFF", 4);
|
||||
int file_size = 36 + data_size;
|
||||
f.write(reinterpret_cast<const char*>(&file_size), 4);
|
||||
f.write("WAVE", 4);
|
||||
|
||||
f.write("fmt ", 4);
|
||||
int fmt_size = 16;
|
||||
f.write(reinterpret_cast<const char*>(&fmt_size), 4);
|
||||
int16_t audio_fmt = 1;
|
||||
f.write(reinterpret_cast<const char*>(&audio_fmt), 2);
|
||||
f.write(reinterpret_cast<const char*>(&channels), 2);
|
||||
f.write(reinterpret_cast<const char*>(&sample_rate), 4);
|
||||
f.write(reinterpret_cast<const char*>(&bytes_per_sec), 4);
|
||||
f.write(reinterpret_cast<const char*>(&block_align), 2);
|
||||
f.write(reinterpret_cast<const char*>(&bits), 2);
|
||||
|
||||
f.write("data", 4);
|
||||
f.write(reinterpret_cast<const char*>(&data_size), 4);
|
||||
|
||||
for (int i = 0; i < samples * channels; i++) {
|
||||
float val = std::max(-1.0f, std::min(1.0f, data[i]));
|
||||
int32_t ival = static_cast<int32_t>(val * 8388607.0f);
|
||||
unsigned char bytes[3];
|
||||
bytes[0] = ival & 0xff;
|
||||
bytes[1] = (ival >> 8) & 0xff;
|
||||
bytes[2] = (ival >> 16) & 0xff;
|
||||
f.write(reinterpret_cast<const char*>(bytes), 3);
|
||||
}
|
||||
}
|
||||
|
||||
int main(int argc, char* argv[]) {
|
||||
if (argc < 3) {
|
||||
std::cerr << "Usage: " << argv[0] << " input.wav output.wav" << std::endl;
|
||||
return 1;
|
||||
}
|
||||
|
||||
std::vector<float> input;
|
||||
float sr = read_wav16(argv[1], input);
|
||||
if (sr <= 0 || input.empty()) {
|
||||
std::cerr << "Failed to read input file" << std::endl;
|
||||
return 1;
|
||||
}
|
||||
|
||||
size_t total_samples = input.size();
|
||||
int channels = 2;
|
||||
size_t frames = total_samples / channels;
|
||||
|
||||
std::vector<float> output(total_samples);
|
||||
|
||||
SpectralProcessor sp(2048, 512);
|
||||
|
||||
std::vector<float> left_in(frames), right_in(frames);
|
||||
for (size_t i = 0; i < frames; i++) {
|
||||
left_in[i] = input[i * 2];
|
||||
right_in[i] = input[i * 2 + 1];
|
||||
}
|
||||
|
||||
std::vector<float> left(frames, 0.0f), right(frames, 0.0f);
|
||||
encode_ms(left_in.data(), right_in.data(), frames);
|
||||
sp.processBlock(left_in.data(), left.data(), frames, 1);
|
||||
sp.processBlock(right_in.data(), right.data(), frames, 1);
|
||||
decode_ms(left.data(), right.data(), frames);
|
||||
|
||||
for (size_t i = 0; i < frames; i++) {
|
||||
output[i * 2] = left[i];
|
||||
output[i * 2 + 1] = right[i];
|
||||
}
|
||||
|
||||
write_wav24(argv[2], output.data(), frames, channels, static_cast<int>(sr));
|
||||
|
||||
std::cout << "Done!" << std::endl;
|
||||
|
||||
return 0;
|
||||
}
|
||||
Reference in New Issue
Block a user