5D Library › Singer Formant Clustering, Glottal Closure Quotients and Acoustic Authority Psychophysics · 中文
Chapter 5. From Measures to Ratings: What a Regression of Trust on Voice Can Recover
A synthetic rating study
Listeners do respond to voices: lower-pitched voices, for example, are preferred for leadership in experiments with both men and women (Klofstad et al. 2012). The claim to check is a stronger one, that a multiple regression gives reliable “weights” of jitter, shimmer, final fall and pause ratio on trust and dominance. p09 simulates a study of 120 rated recordings in which the true weights are known.
Calculation
# Chapter 5. p09: What a regression of "trust" ratings on voice measures
# can recover. 120 synthetic recordings, each rated for trust (mean of
# a listener panel, 1 to 7). Measures: mean F0 (st above 100 Hz),
# jitter %, shimmer % (correlated with jitter, r about 0.7), final slope
# (st/s; more negative = stronger fall) and pause ratio (correlated with
# the fall, r about 0.5). True model: trust = 4 - 0.10 F0 - 0.30 jitter
# - 0.05 shimmer - 0.03 slope - 30 (pause - 0.21)^2 + noise (sd 0.5);
# the square expands to 12.6 pause - 30 pause^2 plus a constant.
# Ordinary least squares with pause and pause^2; standard errors and
# variance inflation factors (VIF). Seed 99.
import random
from math import sqrt
def solve(a, b):
n = len(a)
m = [row[:] + [v] for row, v in zip(a, b)]
for i in range(n):
p = max(range(i, n), key=lambda r: abs(m[r][i]))
m[i], m[p] = m[p], m[i]
for r in range(n):
if r != i:
f = m[r][i] / m[i][i]
m[r] = [x - f * y for x, y in zip(m[r], m[i])]
return [m[i][n] / m[i][i] for i in range(n)]
def ols(rows, y):
k = len(rows[0])
xtx = [[sum(r[i] * r[j] for r in rows) for j in range(k)]
for i in range(k)]
beta = solve(xtx, [sum(r[i] * v for r, v in zip(rows, y))
for i in range(k)])
res = [v - sum(b * x for b, x in zip(beta, r)) for r, v in zip(rows, y)]
s2 = sum(e * e for e in res) / (len(y) - k)
inv = [solve(xtx, [1.0 if i == j else 0.0 for i in range(k)])
for j in range(k)]
return beta, [sqrt(s2 * inv[i][i]) for i in range(k)], res
def r2(rows, y):
_, _, res = ols(rows, y)
m = sum(y) / len(y)
return 1 - sum(e * e for e in res) / sum((v - m) ** 2 for v in y)
NAMES = ("F0 (st)", "jitter %", "shimmer %", "final slope", "pause",
"pause^2")
TRUE = (-0.10, -0.30, -0.05, -0.03, 12.6, -30.0)
if __name__ == "__main__":
rng = random.Random(99)
rows, y = [], []
for _ in range(120):
f0 = rng.gauss(2, 2)
z = rng.gauss(0, 1)
jit = 0.6 + 0.2 * z
shim = 3.0 + 0.8 * (0.7 * z + 0.714 * rng.gauss(0, 1))
w = rng.gauss(0, 1)
slope = -8 + 6 * w
pause = 0.20 + 0.06 * (-0.5 * w + 0.866 * rng.gauss(0, 1))
t = (4 - 0.10 * f0 - 0.30 * jit - 0.05 * shim - 0.03 * slope
- 30 * (pause - 0.21) ** 2 + rng.gauss(0, 0.5))
rows.append([1.0, f0, jit, shim, slope, pause, pause * pause])
y.append(t)
beta, se, _ = ols(rows, y)
print(" measure true estimate s.e. t VIF")
for i, name in enumerate(NAMES, 1):
others = [[r[0]] + [r[j] for j in range(1, 7) if j != i]
for r in rows]
vif = 1 / (1 - r2(others, [r[i] for r in rows]))
tv = "{:6.2f}".format(TRUE[i - 1])
print(" {:<12} {} {:9.3f} {:6.3f} {:5.1f} {:7.1f}".format(
name, tv, beta[i], se[i], beta[i] / se[i], vif))
print(" model R^2 {:.3f}".format(r2(rows, y)))
# measure true estimate s.e. t VIF
# F0 (st) -0.10 -0.110 0.023 -4.8 1.0
# jitter % -0.30 -0.123 0.318 -0.4 2.4
# shimmer % -0.05 -0.048 0.084 -0.6 2.5
# final slope -0.03 -0.038 0.009 -4.4 1.4
# pause 12.60 14.176 3.318 4.3 20.3
# pause^2 -30.00 -33.448 8.243 -4.1 20.1
# model R^2 0.386The regression recovers the effects that are large relative to their spread: mean pitch (-0.110 against a true -0.10, t of -4.8) and the final slope (-0.038 against -0.03). It does not recover jitter: the estimate is -0.123 with a standard error of 0.318, although the true weight is -0.30, because jitter and shimmer move together (variance inflation 2.4 and 2.5) and vary little within a healthy sample. The pause terms are recovered, with variance inflation of about 20, which is built in when a variable and its square enter together. The model explains 0.386 of the variance; a published “weight” from such a study is a statement about that sample’s spread of voices as much as about listeners.
The best pause ratio
p10 asks whether a study can locate the optimum of an inverted U, here a true optimum of 0.21, inside the popular 0.18 to 0.25 band.
Calculation
# Chapter 5. p10: Can a study pin down the "best" pause ratio? Trust =
# a - c (pause - 0.21)^2 + noise (sd 0.6), with pause ratios spread as
# in p09 (mean 0.20, sd 0.06). Each simulated study has N recordings,
# fits a + b1 pause + b2 pause^2 by least squares and reports the
# optimum -b1 / (2 b2). Curvature c = 30 (as in p09) or 10 (a flatter
# hill). 2,000 studies per case, seed 99.
import random
def fit(xs, ys):
n = len(xs)
s = [sum(x ** k for x in xs) for k in range(5)]
t = [sum(y * x ** k for x, y in zip(xs, ys)) for k in range(3)]
a = [[s[0], s[1], s[2]], [s[1], s[2], s[3]], [s[2], s[3], s[4]]]
for i in range(3):
for r in range(3):
if r != i:
f = a[r][i] / a[i][i]
a[r] = [u - f * v for u, v in zip(a[r], a[i])]
t[r] -= f * t[i]
return [t[i] / a[i][i] for i in range(3)] if n else None
if __name__ == "__main__":
rng = random.Random(99)
print(" curvature N optimum 10% median 90% in 0.18-0.25"
" no peak")
for c in (30, 10):
for n in (60, 120, 600):
opts, nopeak = [], 0
for _ in range(2000):
xs = [rng.gauss(0.20, 0.06) for _ in range(n)]
ys = [4 - c * (x - 0.21) ** 2 + rng.gauss(0, 0.6)
for x in xs]
_, b1, b2 = fit(xs, ys)
if b2 >= 0:
nopeak += 1
else:
opts.append(-b1 / (2 * b2))
opts.sort()
q = lambda a: opts[int(a * (len(opts) - 1))]
print(" {:9d} {:4d} {:11.3f} {:7.3f} {:5.3f} {:12.3f}"
" {:7.3f}".format(c, n, q(0.1), q(0.5), q(0.9),
sum(0.18 <= o <= 0.25 for o in opts)
/ 2000, nopeak / 2000))
# curvature N optimum 10% median 90% in 0.18-0.25 no peak
# 30 60 0.179 0.209 0.247 0.767 0.044
# 30 120 0.189 0.210 0.237 0.905 0.004
# 30 600 0.201 0.210 0.220 1.000 0.000
# 10 60 0.139 0.209 0.301 0.402 0.266
# 10 120 0.152 0.207 0.290 0.483 0.185
# 10 600 0.183 0.209 0.245 0.809 0.022With a pronounced hill (curvature 30) and 60 recordings, the estimated optimum falls between 0.179 and 0.247 for eight studies in ten, and inside the band in 0.767 of studies; with 600 recordings in all of them. With a flatter hill (curvature 10), 60 recordings place the optimum between 0.139 and 0.301, inside the band only 0.402 of the time, and 0.266 of studies find no peak at all. Even 600 recordings leave 0.809. A sharp “18% to 25%” band claims more precision than most rating studies can deliver.
Hypothesis · not established
The author’s interpretation (not yet tested): in rating studies of persuasive speech, the estimated optimum pause ratio is less stable across studies than the estimated effect of mean pitch. What would show it wrong: in a meta-analysis of at least five independent rating studies that report both, the between-study spread of the pause optimum, relative to its standard error, is no larger than that of the pitch effect.
Summary
A regression of ratings on voice measures recovers large, independent effects such as mean pitch, but not small, correlated ones such as jitter and shimmer. The optimum of an inverted U needs hundreds of recordings to be located within a band as narrow as 0.18 to 0.25.
References
Fan, Y. (2026). Singer Formant Clustering, Glottal Closure Quotients and Acoustic Authority Psychophysics: Subglottal Pressure Dynamics, Pitch-Floor Stability and Pause-to-Phoneme Persuasion Ratios [歌手共振峰簇、声门闭合商与声学权威度心理物理学] (Version 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090258 · Licensed under Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).