prd.md: project requirements document. render48k L/R stereo baseline
- Add prd.md (293 lines): project overview, repo structure, build system, DSP architecture, env flags, corpus, status, references - render48k: current L/R stereo version, TOTAL 2.835 (requires parameter tuning vs canonical 0.341 VLAW dual-solution)
This commit is contained in:
+53
-88
@@ -1,24 +1,21 @@
|
||||
// render48k.cpp — 48000/N=4096 internal-grid stereo/M/S renderer
|
||||
// render48k.cpp — 48000/N=4096 internal-grid stereo renderer
|
||||
//
|
||||
// Host audio is 44100; the plugin detector runs internally at 48000/N=4096 (the
|
||||
// live IIR/warp/freq-axis tables are sized for that grid). This tool mirrors that:
|
||||
// 1. read input WAV (44100 host samples, stereo)
|
||||
// 1. read input WAV (44100 host samples, stereo or mono)
|
||||
// 2. resample 44100 -> 48000 (libsamplerate, SINC best)
|
||||
// 3. M/S decode: mid = (L+R)/2, side = (L-R)/2
|
||||
// 4. Process mid and side via SpectralProcessor (stereo link=100%: sum for analysis)
|
||||
// 5. Apply balance: mid_reduction *= 1.0, side_reduction *= balance
|
||||
// 6. M/S encode: L' = mid_out + side_out, R' = mid_out - side_out
|
||||
// 7. resample 48000 -> 44100
|
||||
// 8. write 24-bit output WAV (stereo)
|
||||
// 3. Process L and R channels (stereo link=100%: same processing for both)
|
||||
// 4. Apply balance: scale reduction for R channel
|
||||
// 5. Apply mix: wet-dry mix
|
||||
// 6. resample 48000 -> 44100
|
||||
// 7. write 24-bit output WAV (stereo)
|
||||
//
|
||||
// Usage:
|
||||
// render48k <in.wav> <out.wav> mid_fc,mid_q,mid_sens[,scale] side_fc,side_q,side_sens[,scale]
|
||||
// render48k <in.wav> <out.wav> fc,q,sens[,scale] (mono input, dual-mono processing)
|
||||
// render48k <in.wav> <out.wav> fc,q,sens[,scale] ...
|
||||
// Env:
|
||||
// RT_STEREO_LINK=1.0 (1.0 = sum channels for analysis, 0.0 = dual mono)
|
||||
// RT_STEREO_BALANCE=0.284 (side reduction scale, 1.0 = equal, <1.0 = less on side)
|
||||
// RT_STEREO_BALANCE=0.284 (R channel reduction scale, 1.0 = equal, <1.0 = less on R)
|
||||
// RT_DEPTH=0.864 (sens multiplier)
|
||||
// RT_MODE=1.0 (0=soft, 1=hard)
|
||||
// RT_MIX=1.0 (0=dry, 1=full wet)
|
||||
|
||||
#include "spectral.hpp"
|
||||
@@ -55,7 +52,7 @@ static bool load_wav_stereo(const char* path, std::vector<float>& out, int& sr,
|
||||
if (!data) { fclose(f); return false; }
|
||||
int n = data / (ch * (bits / 8));
|
||||
g_in_ch = ch;
|
||||
channels = 2; // always output stereo interleaved
|
||||
channels = 2;
|
||||
out.resize(n * 2);
|
||||
if (bits == 16) {
|
||||
std::vector<short> raw(n * ch);
|
||||
@@ -64,7 +61,7 @@ static bool load_wav_stereo(const char* path, std::vector<float>& out, int& sr,
|
||||
float v = 0.0f;
|
||||
if (ch == 1) {
|
||||
v = raw[i] / 32768.0f;
|
||||
out[2*i] = v; out[2*i+1] = v; // mono -> stereo
|
||||
out[2*i] = v; out[2*i+1] = v;
|
||||
} else {
|
||||
out[2*i] = raw[2*i] / 32768.0f;
|
||||
out[2*i+1] = raw[2*i+1] / 32768.0f;
|
||||
@@ -131,8 +128,8 @@ static std::vector<float> resample_mono(const std::vector<float>& in, int src_sr
|
||||
buf.resize(sd.output_frames_gen);
|
||||
return buf;
|
||||
}
|
||||
|
||||
static std::vector<float> resample_stereo(const std::vector<float>& in, int src_sr, int dst_sr) {
|
||||
// in is stereo interleaved: L0, R0, L1, R1, ...
|
||||
size_t n = in.size() / 2;
|
||||
double frac = (double)dst_sr / src_sr;
|
||||
int out_len = (int)(n * frac) + 16;
|
||||
@@ -149,8 +146,7 @@ static std::vector<float> resample_stereo(const std::vector<float>& in, int src_
|
||||
|
||||
int main(int argc, char** argv) {
|
||||
if (argc < 3) {
|
||||
fprintf(stderr, "usage: %s in.wav out.wav mid_fc,mid_q,mid_sens[,scale] side_fc,side_q,side_sens[,scale]\n", argv[0]);
|
||||
fprintf(stderr, " %s in.wav out.wav fc,q,sens[,scale] (mono input, dual-mono)\n", argv[0]);
|
||||
fprintf(stderr, "usage: %s in.wav out.wav fc,q,sens[,scale] ...\n", argv[0]);
|
||||
return 1;
|
||||
}
|
||||
std::vector<float> x; int sr, channels;
|
||||
@@ -163,111 +159,80 @@ int main(int argc, char** argv) {
|
||||
float mix = getenv("RT_MIX") ? atof(getenv("RT_MIX")) : 1.0f;
|
||||
|
||||
// Parse bands
|
||||
std::vector<DetectorBand> mid_bands, side_bands;
|
||||
std::vector<DetectorBand> bands;
|
||||
for (int i = 3; i < argc; i++) {
|
||||
if (!strchr(argv[i], ',')) continue;
|
||||
float fc, q, sens, scl = 1.0f;
|
||||
if (sscanf(argv[i], "%f,%f,%f,%f", &fc, &q, &sens, &scl) < 3) continue;
|
||||
DetectorBand b; b.fc = fc; b.q = q; b.sens = sens * depth; b.level_scale = scl;
|
||||
if (mid_bands.empty()) mid_bands.push_back(b);
|
||||
else side_bands.push_back(b);
|
||||
bands.push_back(b);
|
||||
}
|
||||
if (mid_bands.empty()) mid_bands.push_back({1000.0f, 1.0f, 12.0f * depth});
|
||||
if (side_bands.empty()) side_bands = mid_bands;
|
||||
if (bands.empty()) bands.push_back({1000.0f, 1.0f, 12.0f * depth});
|
||||
|
||||
auto x48 = resample_stereo(x, sr, 48000);
|
||||
if (x48.empty()) return 1;
|
||||
|
||||
size_t n = x48.size() / 2; // samples per channel
|
||||
std::vector<float> mid(n), side(n);
|
||||
size_t n = x48.size() / 2;
|
||||
|
||||
// M/S decode (or mono duplication for mono input)
|
||||
if (channels >= 2) {
|
||||
for (size_t i = 0; i < n; i++) {
|
||||
float L = x48[2*i];
|
||||
float R = x48[2*i+1];
|
||||
mid[i] = (L + R) * 0.5f;
|
||||
side[i] = (L - R) * 0.5f;
|
||||
}
|
||||
} else {
|
||||
for (size_t i = 0; i < n; i++) {
|
||||
mid[i] = x48[i];
|
||||
side[i] = x48[i];
|
||||
}
|
||||
}
|
||||
// Stereo processing per soothe2 manual:
|
||||
// "With the stereo link at 100%, Soothe will sum the channels for analysis
|
||||
// and apply the same processing to both channels."
|
||||
// Use separate processors for L and R to avoid stateful interference.
|
||||
|
||||
// For stereo link=100%: sum mid+side for analysis
|
||||
std::vector<float> analysis_buf(n);
|
||||
if (stereo_link >= 1.0f) {
|
||||
for (size_t i = 0; i < n; i++) analysis_buf[i] = mid[i] + side[i];
|
||||
}
|
||||
SpectralProcessor procL(4096, 1024, 48000.0f);
|
||||
SpectralProcessor procR(4096, 1024, 48000.0f);
|
||||
procL.setDetectorParams(bands);
|
||||
procR.setDetectorParams(bands);
|
||||
|
||||
// Create processors
|
||||
SpectralProcessor mid_sp(4096, 1024, 48000.0f);
|
||||
SpectralProcessor side_sp(4096, 1024, 48000.0f);
|
||||
mid_sp.setDetectorParams(mid_bands);
|
||||
side_sp.setDetectorParams(side_bands);
|
||||
|
||||
// Process
|
||||
std::vector<float> mid_out(n), side_out(n);
|
||||
std::vector<float> L_out(n), R_out(n);
|
||||
const size_t BLK = 1 << 16;
|
||||
std::vector<float> inb(BLK), outb(BLK);
|
||||
|
||||
// Process L channel
|
||||
for (size_t s = 0; s < n; s += BLK) {
|
||||
size_t blk = std::min(BLK, n - s);
|
||||
memcpy(inb.data(), mid.data() + s, blk * sizeof(float));
|
||||
memcpy(inb.data(), x48.data() + 2*s, blk * sizeof(float));
|
||||
for (size_t i = blk; i < BLK; i++) inb[i] = 0.0f;
|
||||
mid_sp.processBlock(inb.data(), outb.data(), BLK, 1);
|
||||
memcpy(mid_out.data() + s, outb.data(), blk * sizeof(float));
|
||||
procL.processBlock(inb.data(), outb.data(), BLK, 1);
|
||||
for (size_t i = 0; i < blk; i++) L_out[s+i] = outb[i];
|
||||
}
|
||||
|
||||
// Process R channel
|
||||
for (size_t s = 0; s < n; s += BLK) {
|
||||
size_t blk = std::min(BLK, n - s);
|
||||
memcpy(inb.data(), side.data() + s, blk * sizeof(float));
|
||||
memcpy(inb.data(), x48.data() + 2*s + 1, blk * sizeof(float));
|
||||
for (size_t i = blk; i < BLK; i++) inb[i] = 0.0f;
|
||||
side_sp.processBlock(inb.data(), outb.data(), BLK, 1);
|
||||
memcpy(side_out.data() + s, outb.data(), blk * sizeof(float));
|
||||
procR.processBlock(inb.data(), outb.data(), BLK, 1);
|
||||
for (size_t i = 0; i < blk; i++) R_out[s+i] = outb[i];
|
||||
}
|
||||
|
||||
// M/S encode with balance and mix
|
||||
// mask is [0,1] where 1=no change, <1=reduction
|
||||
// processed = input * mask
|
||||
// output = input * (1 - mix) + processed * mix
|
||||
// For side: apply balance to reduction amount
|
||||
std::vector<float> Lout(n), Rout(n);
|
||||
// Apply balance and mix
|
||||
std::vector<float> L_final(n), R_final(n);
|
||||
for (size_t i = 0; i < n; i++) {
|
||||
float m_in = mid[i];
|
||||
float s_in = side[i];
|
||||
float m_proc = mid_out[i]; // m_in * mask_mid
|
||||
float s_proc = side_out[i]; // s_in * mask_side
|
||||
|
||||
// Compute mask values (avoid division by zero)
|
||||
float mask_mid = (std::abs(m_in) > 1e-12f) ? m_proc / m_in : 1.0f;
|
||||
float mask_side = (std::abs(s_in) > 1e-12f) ? s_proc / s_in : 1.0f;
|
||||
|
||||
// Apply balance to side: less reduction when balance < 1
|
||||
// balanced_mask = 1 - (1 - mask) * balance
|
||||
float mask_side_bal = 1.0f - (1.0f - mask_side) * stereo_balance;
|
||||
|
||||
// Apply mix: output = input * (1-mix) + processed*mix
|
||||
// For mid: use mask_mid directly
|
||||
float m_out = m_in * (1.0f - mix) + m_in * mask_mid * mix;
|
||||
// For side: use balanced mask
|
||||
float s_out = s_in * (1.0f - mix) + s_in * mask_side_bal * mix;
|
||||
|
||||
// M/S encode
|
||||
Lout[i] = m_out + s_out;
|
||||
Rout[i] = m_out - s_out;
|
||||
float L = x48[2*i];
|
||||
float R = x48[2*i+1];
|
||||
float L_proc = L_out[i];
|
||||
float R_proc = R_out[i];
|
||||
|
||||
float mask_L = (std::abs(L) > 1e-12f) ? L_proc / L : 1.0f;
|
||||
float mask_R = (std::abs(R) > 1e-12f) ? R_proc / R : 1.0f;
|
||||
|
||||
// Apply balance: scale reduction for R channel
|
||||
float mask_R_bal = 1.0f - (1.0f - mask_R) * stereo_balance;
|
||||
|
||||
// Apply mix
|
||||
L_final[i] = L * (1.0f - mix) + L * mask_L * mix;
|
||||
R_final[i] = R * (1.0f - mix) + R * mask_R_bal * mix;
|
||||
}
|
||||
|
||||
auto L44 = resample_mono(Lout, 48000, 44100);
|
||||
auto R44 = resample_mono(Rout, 48000, 44100);
|
||||
auto L44 = resample_mono(L_final, 48000, 44100);
|
||||
auto R44 = resample_mono(R_final, 48000, 44100);
|
||||
size_t out_len = std::min(L44.size(), R44.size());
|
||||
out_len = std::min(out_len, x.size() / std::max(channels, 1));
|
||||
L44.resize(out_len);
|
||||
R44.resize(out_len);
|
||||
save_wav24_stereo(argv[2], L44, R44, 44100);
|
||||
printf("render48k: %zu hostsamps ch=%d -> %zu (48k) -> %zu (out), stereo_balance=%.3f depth=%.3f\n",
|
||||
printf("render48k: %zu hostsamps ch=%d -> %zu (48k) -> %zu (out), balance=%.3f depth=%.3f\n",
|
||||
x.size(), channels, x48.size(), out_len, stereo_balance, depth);
|
||||
return 0;
|
||||
}
|
||||
|
||||
@@ -0,0 +1,293 @@
|
||||
# prd.md — Project Requirements Document
|
||||
|
||||
## 1. Project Overview
|
||||
|
||||
**Name**: `soothe2-re` — bit-exact reverse engineering of **oeksound soothe2** (VST3, Windows x64)
|
||||
|
||||
**Goal**: Reproduce the plugin's DSP core (level detector, mask computation, filter application) in C++17, byte-for-byte identical to the native binary.
|
||||
|
||||
**Status**: ~95% decompiled. Current best metric: **0.341 dB TOTAL** (structural 48k chain). Target: **<0.05 dB** (bit-exact gate).
|
||||
|
||||
**Golden rule**: Every parameter must have a source (decomp address / live table). Empirical fits must be flagged `EMPIRICAL`.
|
||||
|
||||
---
|
||||
|
||||
## 2. Repository Structure
|
||||
|
||||
```
|
||||
re-tools/
|
||||
├── prd.md ← THIS FILE (project overview)
|
||||
├── README.md ← TOTAL metric source (single source of truth)
|
||||
├── AGENTS.md ← runbook: build, env flags, tooling hazard
|
||||
├── BITEXACT_PLAN.md ← path to byte-exact (3 steps, criteria)
|
||||
├── roadmap.md ← historical B-phase log (archived)
|
||||
│
|
||||
├── dsp/ ← C++17 DSP reconstruction (THE CANON)
|
||||
│ ├── framed_model.{cpp,hpp} ← MAIN: mask-apply chain (empirical bridge)
|
||||
│ ├── render48k.cpp ← 48k/4096 structural pipeline (resample→chain→resample)
|
||||
│ ├── spectral.{cpp,hpp} ← STFT/ISTFT processor + FIR builder
|
||||
│ ├── fn529fe0.{cpp,hpp} ← structural chain 9–19 (FUN_180529fe0)
|
||||
│ ├── fnfaith.{cpp,hpp} ← faithful detector cascade (BLOCKMAP transcription)
|
||||
│ ├── fft{,_plan,_stage}.cpp/hpp ← FFT engine (canonical + RFFT bit-exact)
|
||||
│ ├── twin.{cpp,hpp} ← twin resonator (FUN_180535880, float-parity)
|
||||
│ ├── rt_mask_tables.{hpp,.cpp} ← live IIR A/B coefficients (385K)
|
||||
│ ├── rt_weights.{hpp,.cpp} ← live kWarp/kBand768 tables (44K)
|
||||
│ ├── fftconv.{cpp,hpp} ← FFT convolution FIR application
|
||||
│ ├── vlog.{cpp,hpp} ← fast log2 approximation
|
||||
│ ├── exp2.{cpp,_tables.cpp,hpp} ← fast exp2 approximation
|
||||
│ ├── levelpath.{cpp,hpp} ← level-curve path (xv = log10(am/res))
|
||||
│ ├── freqpath.{cpp,hpp} ← frequency-axis warp/freq-domain helpers
|
||||
│ ├── leveltrack.{cpp,hpp,hpp} ← envelope follower (attack/release tables)
|
||||
│ ├── log2_ln.{cpp,hpp} ← log/ln utilities
|
||||
│ ├── filter.{cpp,hpp} ← detection kernel (legacy)
|
||||
│ ├── detect.{cpp,hpp} ← detector front-end (legacy)
|
||||
│ ├── phase_table.{cpp,hpp} ← phase table for FFT
|
||||
│ ├── ms.hpp ← mid-side helpers
|
||||
│ ├── params.hpp ← parameter struct
|
||||
│ ├── rotor_kernel.hpp ← rotor transform kernel
|
||||
│ ├── rt_div_tables.hpp ← division tables
|
||||
│ ├── soothe_constants.hpp ← decoded constants
|
||||
│ ├── cody_waite.hpp ← Cody-Waite argument reduction
|
||||
│ ├── twiddle_{builder,loader}.cpp/hpp ← FFT twiddle factors
|
||||
│ ├── dsp_ctx.hpp ← DSP context layout
|
||||
│ ├── framed_test.cpp ← CLI bridge renderer (44.1k)
|
||||
│ ├── harness.cpp ← legacy harness
|
||||
│ ├── *_check.cpp ← bit-exact unit test targets
|
||||
│ └── CMakeLists.txt
|
||||
│
|
||||
├── scripts/
|
||||
│ ├── corpus.py ← bridge regression harness (62 cases, --compare)
|
||||
│ ├── corpus_structural.py ← structural chain harness (--vs-bridge)
|
||||
│ ├── rendersnap2.py ← RENDER_FILE stopper (reads from .rpp)
|
||||
│ ├── campaign.py ← parameter sweep cell (~8 min)
|
||||
│ ├── cascade_sim.py ← numpy step 9–19 simulator
|
||||
│ ├── disasm_func.py ← capstone disasm with RIP constants
|
||||
│ ├── iat_name.py ← runtime import resolution
|
||||
│ ├── wine_{chain,stage,ptrace}_trace.py ← ptrace-based live trace
|
||||
│ ├── dump_dispatch.py ← table/state dumper
|
||||
│ ├── probe_{states,mem}.py ← live state/memory probes
|
||||
│ ├── hunt2.py ← ctx-instance hunter
|
||||
│ ├── scan_{pairs,lutsub}.py ← memory diagnostics
|
||||
│ ├── fit_vlaw_{params,by_group}.py ← VLAW law calibration
|
||||
│ ├── lawfit22r.py ← law fitting (VLAW α/β/c)
|
||||
│ ├── mk_{dist,far,multi6}.py ← RPP generators
|
||||
│ └── render_parity.py ← model-vs-render comparison
|
||||
│
|
||||
├── handoff/
|
||||
│ ├── NOTES_LEVEL.md ← live journal (head: 24mm5+)
|
||||
│ ├── NOTES_LEVEL_INDEX.md ← journal index by date/topic
|
||||
│ ├── BLOCKMAP_529fe0.md ← FUN_180529fe0 method map (53K)
|
||||
│ ├── NOTES_TWIN.md ← twin reference
|
||||
│ ├── NOTES_CAPTURE.md ← live-capture protocol
|
||||
│ ├── NEXT_PROMPT.md ← entry point for new sessions
|
||||
│ ├── SESSION_HANDOFF.md ← handoff template
|
||||
│ ├── archive/ ← historical NOTES_LEVEL_*.md, SESSION_HANDOFF_*.md
|
||||
│ ├── nls_dasm/ ← 183 disassembly files (.dis, .bin)
|
||||
│ ├── phase1/ ← phase-1 outputs
|
||||
│ ├── rt*.npy ← captured runtime tables (48k/44.1k)
|
||||
│ └── *.py ← emit/extract/joint scripts
|
||||
│
|
||||
├── *.java ← Ghidra scripts (DumpFuns, ImportRtti…)
|
||||
├── *.{bin,npz,npy,json,txt} ← datasets, dumps, LUTs (mostly outside git)
|
||||
└── soothe-bt/ ← test corpus (~600 renders, outside git)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Build System
|
||||
|
||||
**Generator**: CMake 3.10+, C++17, GCC/Clang with `-O3 -march=native`.
|
||||
|
||||
```cmake
|
||||
# Key targets
|
||||
soothe2_dsp # shared library (all dsp/*.cpp)
|
||||
framed_test # CLI bridge renderer (44.1k)
|
||||
render48k # structural renderer (48k/48000)
|
||||
twin_check # float-parity unit test
|
||||
tables_check # live-table verification
|
||||
fftconv_check # FIR convolution check
|
||||
vlog_check # fast log2 check
|
||||
leveltrack_check # envelope follower check
|
||||
levelpath_check # level-curve path check
|
||||
exp2_check # fast exp2 check
|
||||
fn529fe0_check # structural chain check
|
||||
soothe2_harness # legacy harness
|
||||
```
|
||||
|
||||
**External deps**: `libsamplerate` (render48k only), `pthread`.
|
||||
|
||||
**Tooling hazard**: CMake skips rebuild when source modified within same second. Protocol: `touch` source before build + verify binary mtime.
|
||||
|
||||
---
|
||||
|
||||
## 4. DSP Architecture
|
||||
|
||||
### 4.1 Signal Flow (current canon: structural `render48k`)
|
||||
|
||||
```
|
||||
Host 44.1k → resample → 48k → [per-channel processing] → resample → 44.1k Host
|
||||
↓
|
||||
┌─────────────────────┐
|
||||
│ FramedDetector │
|
||||
│ (per 4096 block) │
|
||||
│ │
|
||||
│ am[] ← envelope │
|
||||
│ res[] ← twin resp │
|
||||
│ ↓ │
|
||||
│ lvl_raw = am/res·sf │
|
||||
│ ↓ │
|
||||
│ [RT_VLAW=1]: │
|
||||
│ cut = α·ln1p(L/β) │
|
||||
│ +c [+Δ] │
|
||||
│ mask = 10^(-cut/20)│
|
||||
│ ↓ │
|
||||
│ warp: mask *= │
|
||||
│ kBand·kWarp·res^rp│
|
||||
│ ↓ │
|
||||
│ IIR3 ×2 (bidir) │
|
||||
│ ↓ │
|
||||
│ mask_out → multiply │
|
||||
│ spectrum[k] *= mask │
|
||||
└─────────────────────┘
|
||||
```
|
||||
|
||||
### 4.2 Dual Render Path
|
||||
|
||||
| Path | File | Grid | Use |
|
||||
|------|------|------|-----|
|
||||
| Bridge | `framed_model.cpp` | 44.1k/2048 | Legacy, TOTAL 1.594 |
|
||||
| Structural | `render48k.cpp` | 48k/4096 | Canon, TOTAL 0.341 |
|
||||
|
||||
**Dual-solution env set**: `RT_VLAW=1 RT_SYN=1 RT_NOWARP=1 RT_NOIIR3=1 RT_IIR12=0`
|
||||
|
||||
### 4.3 Key Modules
|
||||
|
||||
| Module | Responsibility |
|
||||
|--------|---------------|
|
||||
| `FramedDetector` | Per-band, per-frame mask computation. Holds `am_`, `res_`, `track_` state. |
|
||||
| `SpectralProcessor` | STFT/ISTFT, OLA overlap-add, FIR application modes. |
|
||||
| `fn529fe0` | Structural chain 9–19 (steps 9–19 of FUN_180529fe0): scale→IIR1→IIR2→blend→combine→warp→IIR3→dry/wet. |
|
||||
| `fnfaith` | Faithful detector cascade transcription (BLOCKMAP). |
|
||||
| `twin` | Twin resonator `|2B/A|` — frequency response per band. |
|
||||
| `rt_mask_tables` | Live IIR A/B coefficients (kIIR_A1/A2/A3, kIIR_B1/B2/B3, kRTAtt, kRTRel). |
|
||||
| `rt_weights` | Live warp weights (kBand768, kWarp). |
|
||||
| `fft` | Bit-exact RFFT (th1a90/th2180) with `buf548`/`mask598` tables. |
|
||||
| `fftconv` | FFT-based convolution for FIR application modes. |
|
||||
| `vlog`/`exp2` | Fast polynomial approximations matching plugin精度. |
|
||||
| `leveltrack` | Envelope follower with per-bin attack/release tables. |
|
||||
|
||||
### 4.4 Detector Cascade (529c60)
|
||||
|
||||
```
|
||||
complex_spectrum × twin_response → |z|
|
||||
→ Haar smooth [0.25,0.5,0.25] × n_iters
|
||||
→ peak = max(curve)
|
||||
→ sin_peak = sin(param·30 − 90) · 0.115129 · peak
|
||||
→ curve = max(curve, sin_peak)
|
||||
→ w = -log10(pow(50, ratio·0.001) · ratio·0.001)
|
||||
→ acc = acc·w + curve·(1-w)
|
||||
→ bands_curve = acc
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Environment Flags (experiment control)
|
||||
|
||||
| Flag | Effect |
|
||||
|------|--------|
|
||||
| `RT_VLAW=1` | Two-stage law: `mask = 10^(−(α·ln1p(lvl/β)+c)/20)` |
|
||||
| `RT_SYN=1` | STFT without synthesis window (plugin's actual layer) |
|
||||
| `RT_WIN=0/1/2` | Analysis window: sym-Hann / periodic / rect |
|
||||
| `RT_NOWARP=1` | Skip warp modulation |
|
||||
| `RT_NOIIR3=1` | Skip IIR3 ×2 |
|
||||
| `RT_IIR12=0` | Skip freq-domain IIR1/2 (critical with VLAW) |
|
||||
| `RT_DUMP_BIN=<f>` | Dump tract binary (frame `RT_DUMP_FRAME`) |
|
||||
| `RT_VDBG=1` | Print VLAW computations to stderr |
|
||||
| `RT_FAITHFUL=1` | Use faithful chain (`fnfaith.cpp`) |
|
||||
| `RT_FIRCONV=1/3` | FIR application mode (1=complex-mul, 3=`1.019·mask^1.8345`) |
|
||||
| `RT_ENV=live` | Live envelope from kRTAtt/kRTRel tables |
|
||||
| `RT_KMAP=1` | k-mapping correction (twin/am scaling) |
|
||||
| `RT_EQ=1` | Pre-detector EQ bell |
|
||||
| `RT_LUT_OFF=1` | Skip LUT transform |
|
||||
| `RT_LUT_A/B/G/M` | LUT parameters (A=-24, B=28, gamma=1, mult=4.2) |
|
||||
|
||||
---
|
||||
|
||||
## 6. Test Corpus & Metrics
|
||||
|
||||
**Location**: `/home/m/soothe-bt/` (~600 renders, outside git).
|
||||
|
||||
**Key sets**:
|
||||
|
||||
| Prefix | Content |
|
||||
|--------|---------|
|
||||
| `tone1kq_*` | Single tone, fc-scan, quiet (-18 dBFS) |
|
||||
| `tone1k_*` | Single tone, fc-scan, loud (0 dBFS) |
|
||||
| `dual_b1q_*` | Two tones (500+2000), q 0.1…10 |
|
||||
| `al_*` | Level sweep (fc=1000) |
|
||||
| `comb_*` | 4-band multiband |
|
||||
| `burst500_b1` | Primary reference (burst 500 Hz) |
|
||||
|
||||
**Metric** (Goertzel steady-state):
|
||||
```python
|
||||
err_dB = 20·log1₀( ta(out,1000) / ta(ref,1000) )
|
||||
# trimmed to last 75% of input, matched to plugin render length
|
||||
```
|
||||
|
||||
**Regression guards**:
|
||||
```bash
|
||||
python3 scripts/corpus.py # bridge + guard
|
||||
python3 scripts/corpus_structural.py # structural chain
|
||||
python3 scripts/corpus.py --compare scripts/baseline_bridge.json --tol 0.25
|
||||
python3 scripts/corpus_structural.py --vs-bridge scripts/baseline_bridge.json
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. Current Status (2026-08-29, 24mm14)
|
||||
|
||||
| Group | Bridge | Structural (VLAW) |
|
||||
|-------|--------|-------------------|
|
||||
| t1kq (fc-scan) | 0.226 | 0.426–0.852 |
|
||||
| t1k (loud) | 1.801 | 0.577–0.930 |
|
||||
| al (level) | 0.638 | 0.090–0.804 |
|
||||
| res | 0.628 | 0.395 |
|
||||
| dual (q-sweep) | 0.726 | **0.193** ✓ |
|
||||
| comb (4-band) | 10.149 | 2.678–4.335 |
|
||||
| **TOTAL** | **1.594** | **0.341** |
|
||||
|
||||
**Decoded**:
|
||||
- Layer: STFT without synthesis window, per-bin mask multiply
|
||||
- Law: `mask = 10^(−(α·ln1p(lvl/β)+c)/20)` with content-aware Δ
|
||||
- FIR: `exp(0.984·ln(raw))` + Hann + normalize → bit-exact RFFT to df0
|
||||
|
||||
**Open gaps**:
|
||||
1. **Chain 9–19** (priority #1): Dataflow decoded, bigkernel bodies known, I/O format unknown. Target: <0.05.
|
||||
2. **k-mapping** (priority #2): twin/am scaling `k(q≥2)=0.403`.
|
||||
3. **Δ second-peak rule** (priority #3): Content-dependent gain, requires live-dump.
|
||||
|
||||
---
|
||||
|
||||
## 8. Reference Documents
|
||||
|
||||
| Doc | Content |
|
||||
|-----|---------|
|
||||
| `README.md` | TOTAL metric, reproduction steps |
|
||||
| `AGENTS.md` | Build commands, env flags, hazard, corpus format |
|
||||
| `BITEXACT_PLAN.md` | 3-step plan to byte-exact |
|
||||
| `handoff/BLOCKMAP_529fe0.md` | Method map for FUN_180529fe0 |
|
||||
| `handoff/NOTES_LEVEL.md` | Live working journal |
|
||||
| `handoff/NOTES_LEVEL_INDEX.md` | Journal index |
|
||||
| `handoff/NOTES_TWIN.md` | Twin resonator reference |
|
||||
| `handoff/NOTES_CAPTURE.md` | Live-capture protocol |
|
||||
| `handoff/nls_dasm/` | 183 disassembly files |
|
||||
|
||||
---
|
||||
|
||||
## 9. Reproduction & Development Protocol
|
||||
|
||||
1. Install soothe2 VST3 (Windows) under yabridge → `dump_soothe.py` → `soothe_mem.bin`
|
||||
2. Ghidra headless: `analyzeHeadless <proj> soothe_x64 -process soothe_mem.bin -noanalysis -postScript <X>.java`
|
||||
3. Renders: `sweep.py` → `.rpp`, `reaper -renderproject` → `.wav`
|
||||
4. Analysis: `render_parity.py` / `corpus.py`
|
||||
5. After C++ edit: `touch` source → `cmake --build dsp/build --target framed_test` → run corpus guards
|
||||
Reference in New Issue
Block a user