| |
| |
| import io, os, sys |
| import numpy as np, pyarrow.parquet as pq, soundfile as sf |
|
|
| HERE = os.path.dirname(os.path.abspath(__file__)) |
| sys.path.insert(0, HERE) |
| mod = __import__([m for m in ("prosdd_asv19", "prosdd_asv5") if os.path.exists(os.path.join(HERE, m + ".py"))][0]) |
| Cls = getattr(mod, [n for n in dir(mod) if n.startswith("ProSDDASV")][0]) |
| N = int(sys.argv[1]) if len(sys.argv) > 1 else 2000 |
| t = pq.read_table(os.path.join(HERE, "..", "ASVspoof2019_LA", "data", "test-00000-of-00009.parquet"), columns=["audio", "label"]) |
| idx = np.sort(np.random.default_rng(0).choice(t.num_rows, N, replace=False)) |
| t = t.take(idx).to_pylist() |
| m = Cls(); m.load() |
| scores, labels = [], [] |
| B = 16 |
| for k in range(0, len(t), B): |
| rows = t[k:k + B] |
| scores += m.score_batch([sf.read(io.BytesIO(r["audio"]["bytes"]), dtype="float32")[0] for r in rows], [16000] * len(rows)) |
| labels += [r["label"] for r in rows] |
| s, y = np.array(scores), np.array(labels) |
| bona, spoof = s[y == 0], s[y == 1] |
| th = np.sort(s) |
| frr = np.array([(bona < x).mean() for x in th]); far = np.array([(spoof >= x).mean() for x in th]) |
| i = np.argmin(np.abs(frr - far)) |
| print(f"{Cls.__name__} ASVspoof2019_LA subset n={len(s)} bona={len(bona)} spoof={len(spoof)} EER~{100 * (frr[i] + far[i]) / 2:.3f}%") |
|
|
