noise_injection_seq2seq/random_phoneme.py at main · EmergentSystemLabStudent/noise_injection_seq2seq · GitHub

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
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
import numpy as np

phoneme = ["AA",
"AA0",
"AA1",
"AA2",
"AE",
"AE0",
"AE1",
"AE2",
"AH",
"AH0",
"AH1",
"AH2",
"AO",
"AO0",
"AO1",
"AO2",
"AW",
"AW0",
"AW1",
"AW2",
"AY",
"AY0",
"AY1",
"AY2",
"B",
"CH",
"D",
"DH",
"EH",
"EH0",
"EH1",
"EH2",
"ER",
"ER0",
"ER1",
"ER2",
"EY",
"EY0",
"EY1",
"EY2",
"F",
"G",
"HH",
"IH",
"IH0",
"IH1",
"IH2",
"IY",
"IY0",
"IY1",
"IY2",
"JH",
"K",
"L",
"M",
"N",
"NG",
"OW",
"OW0",
"OW1",
"OW2",
"OY",
"OY0",
"OY1",
"OY2",
"P",
"R",
"S",
"SH",
"T",
"TH",
"UH",
"UH0",
"UH1",
"UH2",
"UW",
"UW0",
"UW1",
"UW2",
"V",
"W",
"Y",
"Z",
"ZH"]

cmudict = {"Softner":"S AO F AX N AX"}

def get_random_phoneme():
    index = int(np.random.randint(0, get_number_phoneme(), 1))
    return phoneme[index]

def get_number_phoneme():
    return len(phoneme)