experiments/exp_utterance.py

"""Table 1 utterance-conditioning row / Finding 4 — utterance conditioning: inject the human utterance's acoustics via interaction features
(cosine delivery-match / element-wise products). Plain concatenation cancels in the pairwise difference,
so interactions are the only way the utterance can enter a linear pairwise ranker.

    python experiments/exp_utterance.py          (~3 min)
"""
import sys
import os
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), ".."))
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from experiments import common as C


def nrm(v):
    return v / (np.linalg.norm(v) + 1e-8)


def feature(resp, utt, mode):
    a = C.arr(resp)
    base = np.concatenate([a[r] for r in C.POOL_FINAL])
    if mode == "base":
        return base
    um = C.arr(utt)[C.R_MEAN()]
    resp_parts = [a[C.R_MEAN()], a[C.R_SEG3], a[C.R_SEG3 + 1], a[C.R_SEG3 + 2]]
    if mode == "+cos":
        return np.concatenate([base, np.array([float(nrm(p) @ nrm(um)) for p in resp_parts], dtype=np.float32)])
    if mode == "+prod":
        return np.concatenate([base, a[C.R_MEAN()] * um])
    raise ValueError(mode)


for mode in ["base", "+cos", "+prod"]:
    X, y = [], []
    for it in C.train_items(2500):
        try:
            g, b = feature(it.good_wav, it.utterance_wav, mode), feature(it.bad_wav, it.utterance_wav, mode)
        except Exception:
            continue
        X.append(g - b); y.append(1)
        X.append(b - g); y.append(0)
    X = np.array(X)
    sc = StandardScaler().fit(X)
    clf = LogisticRegression(max_iter=3000, C=0.5).fit(sc.transform(X), y)
    ans = {}
    for q in C.QS:
        fv = sc.transform([feature(o.wav, q.utterance_wav, mode) for o in q.options])
        ans[q.qid] = [o.letter for o in q.options][int(np.argmax(clf.decision_function(fv)))]
    C.report(mode, ans)