Same path as encode_av_inmem.py / decode_av_inmem.py: load_audio_auto (44.1 kHz mono, 8 s) → ensure_max_of_audio → AudioAutoencoder(/group2/ct/weihanx/vae/vae) encode (latent 64×345) → decode. Two inputs per clip: the raw video audio (src) and the new highlighted wav from 8_sec_highlighted_0822 (target). Metrics are sample-aligned waveform SNR / Pearson corr / log-spectral distance (LSD) between VAE input and decoded output.
| id | prompt | src SNR | src corr | src LSD | target SNR | target corr | target LSD | target RMS in→out |
|---|---|---|---|---|---|---|---|---|
Bm3Lfx58wvo_000200 | train | 3.87 | 0.79 | 8.22 | 14.27 | 0.981 | 8.05 | -14.6 → -14.5 |
Bm6puindzsc | birds | 12.32 | 0.97 | 13.25 | 6.56 | 0.888 | 10.57 | -40.6 → -40.7 |
Bm8mxpOSmjw_000070 | melodic percussion instrument | 25.53 | 0.999 | 8.39 | 30.42 | 1.0 | 9.59 | -11.8 → -11.9 |
BmBido0MLFk | idling engine | 5.06 | 0.841 | 11.7 | 6.08 | 0.876 | 9.89 | -16.9 → -17.0 |
BmFzGKRojvA | brass instruments | 32.56 | 1.0 | 8.72 | 33.49 | 1.0 | 8.8 | -14.5 → -14.5 |
PifhBU-mSVA_000010 | infant | 15.33 | 0.986 | 9.0 | 31.35 | 1.0 | 8.97 | -12.5 → -12.6 |
TOBw7DgXbgg_000047 | musician | 14.33 | 0.987 | 8.57 | 23.27 | 0.998 | 7.73 | -12.7 → -12.8 |
xc74uXzCRWk_000013 | harmonica | 9.0 | 0.939 | 11.85 | 10.91 | 0.96 | 9.87 | -17.6 → -17.5 |
U-L9YCIdLbg_000080 | electric guitar | 14.39 | 0.982 | 10.77 | 16.13 | 0.988 | 7.88 | -16.8 → -16.7 |
R93J7u5EWvk | drum kit | 1.66 | 0.657 | 10.56 | 7.96 | 0.921 | 10.36 | -18.0 → -17.9 |
Kz_gp7UE9IY_000001 | dog | 20.61 | 0.996 | 6.67 | 21.58 | 0.997 | 10.3 | -12.6 → -12.9 |
mT49XQjXEvY_000000 | chickens | 6.45 | 0.882 | 8.88 | 6.0 | 0.87 | 10.1 | -16.7 → -17.1 |
hqvqPITWcrA_000260 | siren | 9.21 | 0.941 | 7.93 | 8.63 | 0.932 | 9.7 | -17.9 → -17.9 |
CsMMU1p3Sik_000030 | crowd | 5.51 | 0.859 | 10.65 | 7.0 | 0.899 | 8.1 | -13.0 → -13.2 |
iTdlEJPKT94_000300 | train horn | 6.84 | 0.895 | 12.62 | 13.85 | 0.979 | 10.44 | -22.7 → -22.9 |
Bm3Lfx58wvo_000200 — “train” (first5)video audio roundtrip: SNR 3.87 dB · corr 0.79 · LSD 8.22 dB | highlighted roundtrip: SNR 14.27 dB · corr 0.981 · LSD 8.05 dB · RMS -14.6→-14.5 dBFS

Bm6puindzsc — “birds” (first5)video audio roundtrip: SNR 12.32 dB · corr 0.97 · LSD 13.25 dB | highlighted roundtrip: SNR 6.56 dB · corr 0.888 · LSD 10.57 dB · RMS -40.6→-40.7 dBFS

Bm8mxpOSmjw_000070 — “melodic percussion instrument” (first5)video audio roundtrip: SNR 25.53 dB · corr 0.999 · LSD 8.39 dB | highlighted roundtrip: SNR 30.42 dB · corr 1.0 · LSD 9.59 dB · RMS -11.8→-11.9 dBFS

BmBido0MLFk — “idling engine” (first5)video audio roundtrip: SNR 5.06 dB · corr 0.841 · LSD 11.7 dB | highlighted roundtrip: SNR 6.08 dB · corr 0.876 · LSD 9.89 dB · RMS -16.9→-17.0 dBFS

BmFzGKRojvA — “brass instruments” (first5)video audio roundtrip: SNR 32.56 dB · corr 1.0 · LSD 8.72 dB | highlighted roundtrip: SNR 33.49 dB · corr 1.0 · LSD 8.8 dB · RMS -14.5→-14.5 dBFS

PifhBU-mSVA_000010 — “infant” (multi-source)video audio roundtrip: SNR 15.33 dB · corr 0.986 · LSD 9.0 dB | highlighted roundtrip: SNR 31.35 dB · corr 1.0 · LSD 8.97 dB · RMS -12.5→-12.6 dBFS

TOBw7DgXbgg_000047 — “musician” (multi-source)video audio roundtrip: SNR 14.33 dB · corr 0.987 · LSD 8.57 dB | highlighted roundtrip: SNR 23.27 dB · corr 0.998 · LSD 7.73 dB · RMS -12.7→-12.8 dBFS

xc74uXzCRWk_000013 — “harmonica” (multi-source)video audio roundtrip: SNR 9.0 dB · corr 0.939 · LSD 11.85 dB | highlighted roundtrip: SNR 10.91 dB · corr 0.96 · LSD 9.87 dB · RMS -17.6→-17.5 dBFS

U-L9YCIdLbg_000080 — “electric guitar” (multi-source)video audio roundtrip: SNR 14.39 dB · corr 0.982 · LSD 10.77 dB | highlighted roundtrip: SNR 16.13 dB · corr 0.988 · LSD 7.88 dB · RMS -16.8→-16.7 dBFS

R93J7u5EWvk — “drum kit” (multi-source)video audio roundtrip: SNR 1.66 dB · corr 0.657 · LSD 10.56 dB | highlighted roundtrip: SNR 7.96 dB · corr 0.921 · LSD 10.36 dB · RMS -18.0→-17.9 dBFS

Kz_gp7UE9IY_000001 — “dog” (multi-source)video audio roundtrip: SNR 20.61 dB · corr 0.996 · LSD 6.67 dB | highlighted roundtrip: SNR 21.58 dB · corr 0.997 · LSD 10.3 dB · RMS -12.6→-12.9 dBFS

mT49XQjXEvY_000000 — “chickens” (multi-source)video audio roundtrip: SNR 6.45 dB · corr 0.882 · LSD 8.88 dB | highlighted roundtrip: SNR 6.0 dB · corr 0.87 · LSD 10.1 dB · RMS -16.7→-17.1 dBFS

hqvqPITWcrA_000260 — “siren” (multi-source)video audio roundtrip: SNR 9.21 dB · corr 0.941 · LSD 7.93 dB | highlighted roundtrip: SNR 8.63 dB · corr 0.932 · LSD 9.7 dB · RMS -17.9→-17.9 dBFS

CsMMU1p3Sik_000030 — “crowd” (multi-source)video audio roundtrip: SNR 5.51 dB · corr 0.859 · LSD 10.65 dB | highlighted roundtrip: SNR 7.0 dB · corr 0.899 · LSD 8.1 dB · RMS -13.0→-13.2 dBFS

iTdlEJPKT94_000300 — “train horn” (multi-source)video audio roundtrip: SNR 6.84 dB · corr 0.895 · LSD 12.62 dB | highlighted roundtrip: SNR 13.85 dB · corr 0.979 · LSD 10.44 dB · RMS -22.7→-22.9 dBFS

Built by /group2/ct/weihanx/audio_hl_demo/audio_roundtrip.py + build_roundtrip_space.py