利用spleeter分离歌曲人声并借助Parselmouth绘制声波图像

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79

import parselmouth

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# import math

sns.set()  # Use seaborn's default style to make attractive graphs
snd = parselmouth.Sound(r"audio/vocals.wav")


def draw_pitch(pitch):
    # Extract selected pitch contour, and
    # replace unvoiced samples by NaN to not plot
    pitch_values = pitch.selected_array['frequency']
    pitch_values[pitch_values == 0] = np.nan
    plt.plot(pitch.xs(), pitch_values, 'o', markersize=2, color='w')
    plt.plot(pitch.xs(), pitch_values, 'o', markersize=2)
    plt.grid(False)
    plt.ylim(0, pitch.ceiling)
    plt.ylabel("fundamental frequency [Hz]")


# def draw_spectrogram(spectrogram, dynamic_range=70):
#     X, Y = spectrogram.x_grid(), spectrogram.y_grid()
#     sg_db = 10 * np.log10(spectrogram.values)
#     plt.pcolormesh(X, Y, sg_db, vmin=sg_db.max() - dynamic_range, cmap='afmhot')
#     plt.ylim([spectrogram.ymin, spectrogram.ymax])
#     plt.xlabel("time [s]")
#     plt.ylabel("frequency [Hz]")

# def draw_intensity(intensity):
#     plt.plot(intensity.xs(), intensity.values.T, linewidth=3, color='w')
#     plt.plot(intensity.xs(), intensity.values.T, linewidth=1)
#     plt.grid(False)
#     plt.ylim(0)
#     plt.ylabel("intensity [dB]")


class Tonality:
    base_diff = [0, 2, 4, 5, 7, 9, 11]
    tones = ['A', 'A#', 'B', 'C', 'C#', 'D', "D#", 'E', 'F', 'F#', 'G', 'G#']

    def __init__(self, tone):
        assert tone in self.tones
        self.base_freq = self.tone_to_freq(tone)

    def tone_to_freq(self, tone):
        A_freq = 440
        return A_freq * (2 ** (self.tones.index(tone) / 12))

    def get_freq(self):
        ret = []
        for r in range(-3, 2):
            base = self.base_freq * (2 ** r)
            ret.extend([base * (2 ** (diff / 12)) for diff in self.base_diff])
        return ret


def draw_standard(tone):
    for f in Tonality(tone).get_freq():
        plt.axline((0, f), (1, f), lw=1)


pitch = snd.to_pitch()
# If desired, pre-emphasize the sound fragment before calculating the spectrogram
# pre_emphasized_snd = snd.copy()
# pre_emphasized_snd.pre_emphasize()
# spectrogram = pre_emphasized_snd.to_spectrogram(window_length=0.03, maximum_frequency=8000)
plt.figure()
# draw_spectrogram(spectrogram)
plt.twinx()

tone = 'F#'
draw_standard(tone)
draw_pitch(pitch)
plt.xlim([snd.xmin, snd.xmax])
plt.show()  # or plt.savefig("spectrogram_0.03.pdf")