Matiq/soothe2-re
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
fc48a9fee4227c8c0c20c72cbf65fe87eda32d96
soothe2-re/dsp
T
History
Matiq fc48a9fee4 P4: real mask chain in FramedDetector (level-tracker + accumulator + live-calibrated LUT), t1kq err 0.5dB 
Replace empirical PCHIP detector with live-calibrated mask chain from FUN_180529fe0:
  level = am*res*scale; track += w*(level-track) (per-bin attack/release weights
  extracted from RT snapshot, rt_weights.hpp); acc = (level-track)+level; mask =
  (1/(1+K*acc))^n (K=9.8026 n=0.25966 fitted to live mask band0). min-combine.

Results (N=2048 hop=512): t1kq single-band err +0.51 dB (-14.47 vs -14.98 dB ref);
comb 4-band per-tone -3.4..+5.8 dB (old PCHIP over-cut comb ~6 dB). Adds framed_test
harness for C++ FramedDetector eval on tone1kq/comb.
2026-08-20 13:11:27 +03:00
..
CMakeLists.txt
P4: real mask chain in FramedDetector (level-tracker + accumulator + live-calibrated LUT), t1kq err 0.5dB
2026-08-20 13:11:27 +03:00
cody_waite.hpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
detect.cpp
roadmap: detector decrypted in soothe_mem.bin, SNR 19.8dB; integrate twiddle loader
2026-08-17 20:02:32 +03:00
detect.hpp
dsp/: add spectral detector with envelope + peak suppression
2026-08-17 15:49:48 +03:00
dsp_ctx.hpp
P1.1: embed runtime-captured DSP tables (WIN_WINDOW, FREQAXIS@48k, WA/WB/WC/WD), dsp_ctx registry mirror, tables_check ALL OK
2026-08-19 22:48:32 +03:00
fft_plan.cpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
fft_plan.hpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
fft_stage.cpp
P3.1: extract FFT code from rt snap (extract_fft.py); decode cplx_mul 0x8440 = in-place elementwise double mult, twiddle loader 0x39b00 stride copy, dispatcher 0x535a70->0x140a10/70->jumptable[0x1826159a0]=4; implement cplx_mul_scalar_inplace
2026-08-20 02:25:59 +03:00
fft_stage.hpp
P3.1: extract FFT code from rt snap (extract_fft.py); decode cplx_mul 0x8440 = in-place elementwise double mult, twiddle loader 0x39b00 stride copy, dispatcher 0x535a70->0x140a10/70->jumptable[0x1826159a0]=4; implement cplx_mul_scalar_inplace
2026-08-20 02:25:59 +03:00
fft.cpp
roadmap: detector decrypted in soothe_mem.bin, SNR 19.8dB; integrate twiddle loader
2026-08-17 20:02:32 +03:00
fft.hpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
fftconv_check.cpp
P1.3: integrate FFT-conv stage (build_fir_from_window step5 memcpy + fir_from_mask + overlap-save conv) with captured WIN_WINDOW; fftconv_check confirms FIR=window[2048:4096]={0.8->1.0}
2026-08-19 23:25:21 +03:00
fftconv.cpp
P1.3: integrate FFT-conv stage (build_fir_from_window step5 memcpy + fir_from_mask + overlap-save conv) with captured WIN_WINDOW; fftconv_check confirms FIR=window[2048:4096]={0.8->1.0}
2026-08-19 23:25:21 +03:00
fftconv.hpp
P1.3: integrate FFT-conv stage (build_fir_from_window step5 memcpy + fir_from_mask + overlap-save conv) with captured WIN_WINDOW; fftconv_check confirms FIR=window[2048:4096]={0.8->1.0}
2026-08-19 23:25:21 +03:00
filter.cpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
filter.hpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
framed_model.cpp
P4: real mask chain in FramedDetector (level-tracker + accumulator + live-calibrated LUT), t1kq err 0.5dB
2026-08-20 13:11:27 +03:00
framed_model.hpp
P4: real mask chain in FramedDetector (level-tracker + accumulator + live-calibrated LUT), t1kq err 0.5dB
2026-08-20 13:11:27 +03:00
framed_test.cpp
P4: real mask chain in FramedDetector (level-tracker + accumulator + live-calibrated LUT), t1kq err 0.5dB
2026-08-20 13:11:27 +03:00
freqpath.cpp
dsp: freqpath - warp 0x5406a8 = 0.87*x/(1+x/K) (K=exp(2.0723), x=f/2000) из FUN_180530850 (0x530900) + self-check (rel err 1.5e-07, PASS)
2026-08-18 17:08:42 +03:00
freqpath.hpp
dsp: freqpath - warp 0x5406a8 = 0.87*x/(1+x/K) (K=exp(2.0723), x=f/2000) из FUN_180530850 (0x530900) + self-check (rel err 1.5e-07, PASS)
2026-08-18 17:08:42 +03:00
harness.cpp
P4: multi-band FramedDetector (per-band twin res, sens-scaled GAIN, min-combine); tt_base 61.40%; min-combine wrong (soothe2 uses additive accumulator 0x5407c8)
2026-08-20 10:41:24 +03:00
levelpath_check.cpp
P2: decode mask-accumulator combine kernels from raw bytes — combine3(0x8d60)=sub, acc_add(0x5a20)=dst+=src, acc_fma(0x3c40)=dst+=a·b; implement + levelpath_check ALL OK
2026-08-20 01:30:33 +03:00
levelpath.cpp
P4-prep: eval_lut_bin uses float logf/expf (matches decomp FUN_180563440 logf/expf, not double std::log/exp)
2026-08-20 09:26:38 +03:00
levelpath.hpp
P2: decode mask-accumulator combine kernels from raw bytes — combine3(0x8d60)=sub, acc_add(0x5a20)=dst+=src, acc_fma(0x3c40)=dst+=a·b; implement + levelpath_check ALL OK
2026-08-20 01:30:33 +03:00
leveltrack_check.cpp
P1.5: embed live level-tracker A[] + mask scalars into C++ (dsp/leveltrack_data.hpp); leveltrack_check sanity confirms SR=48000, A_ATTACK plateaus 0.692, attack/release=1.0
2026-08-20 01:12:12 +03:00
leveltrack_data.hpp
P1.5: embed live level-tracker A[] + mask scalars into C++ (dsp/leveltrack_data.hpp); leveltrack_check sanity confirms SR=48000, A_ATTACK plateaus 0.692, attack/release=1.0
2026-08-20 01:12:12 +03:00
leveltrack.cpp
P2: level-tracker UPDATE-loop located (inline bidirectional IIR in FUN_180529fe0), structural module leveltrack (iir_first_order/bidirectional/unrolled4); scalar==unrolled verified; remaining = live A[] coeffs
2026-08-19 23:53:01 +03:00
leveltrack.hpp
P2: level-tracker UPDATE-loop located (inline bidirectional IIR in FUN_180529fe0), structural module leveltrack (iir_first_order/bidirectional/unrolled4); scalar==unrolled verified; remaining = live A[] coeffs
2026-08-19 23:53:01 +03:00
ms.hpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
params.hpp
P0.3-4: harness reads flat params (in/out/[conf]), byte-verified trim; verify_bit_exact.py uses SOURCE WAVE+RENDER_FILE from RPP, sample-report mono/stereo
2026-08-19 22:00:14 +03:00
phase_table.cpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
phase_table.hpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
rotor_kernel.hpp
P0: track twin.cpp/twin.hpp/rotor_kernel.hpp (were shadowed by .gitignore)
2026-08-19 22:00:22 +03:00
rt_weights.cpp
P4: real mask chain in FramedDetector (level-tracker + accumulator + live-calibrated LUT), t1kq err 0.5dB
2026-08-20 13:11:27 +03:00
rt_weights.hpp
P4: real mask chain in FramedDetector (level-tracker + accumulator + live-calibrated LUT), t1kq err 0.5dB
2026-08-20 13:11:27 +03:00
soothe_constants.hpp
dsp/: fix FFT inverse, WOLA normalization, detector model, twiddle loader
2026-08-17 18:39:50 +03:00
spectral.cpp
P4: multi-band FramedDetector (per-band twin res, sens-scaled GAIN, min-combine); tt_base 61.40%; min-combine wrong (soothe2 uses additive accumulator 0x5407c8)
2026-08-20 10:41:24 +03:00
spectral.hpp
P4: multi-band FramedDetector (per-band twin res, sens-scaled GAIN, min-combine); tt_base 61.40%; min-combine wrong (soothe2 uses additive accumulator 0x5407c8)
2026-08-20 10:41:24 +03:00
tables_check.cpp
P1.1: embed runtime-captured DSP tables (WIN_WINDOW, FREQAXIS@48k, WA/WB/WC/WD), dsp_ctx registry mirror, tables_check ALL OK
2026-08-19 22:48:32 +03:00
tables_data.hpp
P1.1: embed runtime-captured DSP tables (WIN_WINDOW, FREQAXIS@48k, WA/WB/WC/WD), dsp_ctx registry mirror, tables_check ALL OK
2026-08-19 22:48:32 +03:00
twiddle_builder.cpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
twiddle_builder.hpp
dsp/: C++ skeleton with working FFT/WOLA STFT
2026-08-17 11:25:35 +03:00
twiddle_loader.hpp
dsp/: fix FFT inverse, WOLA normalization, detector model, twiddle loader
2026-08-17 18:39:50 +03:00
twin_check.cpp
dsp: freqpath - warp 0x5406a8 = 0.87*x/(1+x/K) (K=exp(2.0723), x=f/2000) из FUN_180530850 (0x530900) + self-check (rel err 1.5e-07, PASS)
2026-08-18 17:08:42 +03:00
twin.cpp
P0: track twin.cpp/twin.hpp/rotor_kernel.hpp (were shadowed by .gitignore)
2026-08-19 22:00:22 +03:00
twin.hpp
P0: track twin.cpp/twin.hpp/rotor_kernel.hpp (were shadowed by .gitignore)
2026-08-19 22:00:22 +03:00
vlog_check.cpp
P3.4: transcribe plugin's own vectorized ln(x) (vlog.cpp, minimax ln(1+x) poly + ln2 range-reduction); correct prior misread — dispatch reaches runtime ln, not FFT; vlog_check ALL OK (rel 2.4e-7)
2026-08-20 07:12:56 +03:00
vlog.cpp
P3.4: transcribe plugin's own vectorized ln(x) (vlog.cpp, minimax ln(1+x) poly + ln2 range-reduction); correct prior misread — dispatch reaches runtime ln, not FFT; vlog_check ALL OK (rel 2.4e-7)
2026-08-20 07:12:56 +03:00
vlog.hpp
P3.4: transcribe plugin's own vectorized ln(x) (vlog.cpp, minimax ln(1+x) poly + ln2 range-reduction); correct prior misread — dispatch reaches runtime ln, not FFT; vlog_check ALL OK (rel 2.4e-7)
2026-08-20 07:12:56 +03:00