목소리 확인과 그 판정

# Cosine similarity to a profile's centroid, calibrated on Dad's own 769 kept
# turns against 227 recordings of 49 other voices (cwkPippa doc §7). A voice
# at or above ``match`` is the profile's; below ``uncertain`` it is nobody's;
# between, nobody can say. Measured: other voices topped out at 0.21 (a
# whole turn) and 0.24 (a two-second chunk); 95% of Dad's turns scored above
# 0.49 and 95% of his chunks above 0.38. A chunk is named at ``chunk``. Less
# than ``MIN_IDENTITY_SECONDS`` of speech is a match only at ``short_match``
# (Dad's one-word turns scored 0.37 at the median). The
# ``speaker_thresholds`` setting overrides any of them without a deploy.
DEFAULT_THRESHOLDS = {"match": 0.45, "uncertain": 0.25, "chunk": 0.30, "short_match": 0.60}

# The verdict rule, as verdict_of in cwkPippa's speaker check rules it.
DAD_PROFILE = "dad"
SIGNIFICANT_SECONDS = 1.0     # less speech than this never changes a verdict alone
SURE_STRANGER_SECONDS = 2.0   # an unknown voice alone needs this much to be "other"


def is_dad(v):
    return v.get("profile_id") == DAD_PROFILE and v.get("band") in ("match", "uncertain")


def verdict_of(voices):
    if not voices:
        return "unchecked"
    significant = [v for v in voices if v["seconds"] >= SIGNIFICANT_SECONDS]
    if not significant:
        if any(is_dad(v) and v["band"] == "match" for v in voices):
            return "dad"
        if any(v.get("profile_id") not in (None, DAD_PROFILE) and v["band"] == "match" for v in voices):
            return "other"
        return "uncertain"
    dad = [v for v in significant if is_dad(v)]
    others = [v for v in significant if not is_dad(v)]
    if not others:
        return "dad" if any(v["band"] == "match" for v in dad) else "uncertain"
    if dad:
        return "mixed"
    enrolled = any(v.get("profile_id") not in (None, DAD_PROFILE) and v["band"] == "match" for v in others)
    if enrolled or sum(v["seconds"] for v in others) >= SURE_STRANGER_SECONDS:
        return "other"
    return "uncertain"


def voice(profile, band, seconds):
    return {"profile_id": profile, "band": band, "seconds": seconds}


turns = {
    "an ordinary turn of his": [voice("dad", "match", 6.2)],
    "his voice through wind": [voice("dad", "uncertain", 4.0)],
    "a one-word yes, unsure": [voice("dad", "uncertain", 0.6)],
    "he talks, Mom answers": [voice("dad", "match", 3.1), voice("mom", "match", 2.4)],
    "a guide, 5 s, nobody known": [voice(None, "none", 5.0)],
    "1.4 s of nobody known": [voice(None, "none", 1.4)],
    "Mom alone, short but sure": [voice("mom", "match", 0.8)],
    "a cough beside his sentence": [voice("dad", "match", 5.0), voice(None, "none", 0.4)],
    "no speech found": [],
}
for name, voices in turns.items():
    print(f"{name:<30} -> {verdict_of(voices)}")

# Output:
# an ordinary turn of his        -> dad
# his voice through wind         -> uncertain
# a one-word yes, unsure         -> uncertain
# he talks, Mom answers          -> mixed
# a guide, 5 s, nobody known     -> other
# 1.4 s of nobody known          -> uncertain
# Mom alone, short but sure      -> other
# a cough beside his sentence    -> dad
# no speech found                -> unchecked