implemented tts segmentation data generation
parent
1f60183ab8
commit
3d7542271d
|
|
@ -0,0 +1,141 @@
|
||||||
|
import pandas as pd
|
||||||
|
import pronouncing
|
||||||
|
import re
|
||||||
|
import numpy as np
|
||||||
|
import random
|
||||||
|
|
||||||
|
# mapping = {
|
||||||
|
# s.split()[0]: s.split()[1]
|
||||||
|
# for s in """
|
||||||
|
# AA AA
|
||||||
|
# AE AE
|
||||||
|
# AH UX
|
||||||
|
# AO AO
|
||||||
|
# AW AW
|
||||||
|
# AY AY
|
||||||
|
# B b
|
||||||
|
# CH C
|
||||||
|
# D d
|
||||||
|
# DH D
|
||||||
|
# EH EH
|
||||||
|
# ER UXr
|
||||||
|
# EY EY
|
||||||
|
# F f
|
||||||
|
# G g
|
||||||
|
# HH h
|
||||||
|
# IH IH
|
||||||
|
# IY IY
|
||||||
|
# JH J
|
||||||
|
# K k
|
||||||
|
# L l
|
||||||
|
# M m
|
||||||
|
# N n
|
||||||
|
# NG N
|
||||||
|
# OW OW
|
||||||
|
# OY OY
|
||||||
|
# P p
|
||||||
|
# R r
|
||||||
|
# S s
|
||||||
|
# SH S
|
||||||
|
# T t
|
||||||
|
# TH T
|
||||||
|
# UH UH
|
||||||
|
# UW UW
|
||||||
|
# V v
|
||||||
|
# W w
|
||||||
|
# Y y
|
||||||
|
# Z z
|
||||||
|
# ZH Z
|
||||||
|
# """.strip().split('\n')
|
||||||
|
# }
|
||||||
|
|
||||||
|
# sim_mat = pd.read_csv('./similarity.csv', header=0, index_col=0)
|
||||||
|
#
|
||||||
|
#
|
||||||
|
# def convert_ph(ph):
|
||||||
|
# stress_level = re.search("(\w+)([0-9])", ph)
|
||||||
|
# if stress_level:
|
||||||
|
# return stress_level.group(2) + mapping[stress_level.group(1)]
|
||||||
|
# else:
|
||||||
|
# return mapping[ph]
|
||||||
|
#
|
||||||
|
#
|
||||||
|
# def sim_mat_to_apple_table(smt):
|
||||||
|
# colnames = [convert_ph(ph) for ph in smt.index.tolist()]
|
||||||
|
# smt = pd.DataFrame(np.nan_to_num(smt.values))
|
||||||
|
# fsmt = (smt.T + smt)
|
||||||
|
# np.fill_diagonal(fsmt.values, 100.0)
|
||||||
|
# asmt = pd.DataFrame.copy(fsmt)
|
||||||
|
# asmt.columns = colnames
|
||||||
|
# asmt.index = colnames
|
||||||
|
# apple_sim_table = asmt.stack().reset_index()
|
||||||
|
# apple_sim_table.columns = ['q', 'r', 's']
|
||||||
|
# return apple_sim_table
|
||||||
|
#
|
||||||
|
#
|
||||||
|
# apple_sim_table = sim_mat_to_apple_table(sim_mat)
|
||||||
|
#
|
||||||
|
#
|
||||||
|
# def top_match(ph):
|
||||||
|
# selected = apple_sim_table[(apple_sim_table.q == ph)
|
||||||
|
# & (apple_sim_table.s < 100) &
|
||||||
|
# (apple_sim_table.s >= 70)]
|
||||||
|
# tm = ph
|
||||||
|
# if len(selected) > 0:
|
||||||
|
# tm = pd.DataFrame.sort_values(selected, 's', ascending=False).iloc[0].r
|
||||||
|
# return tm
|
||||||
|
|
||||||
|
|
||||||
|
apple_phonemes = [
|
||||||
|
'%', '@', 'AE', 'EY', 'AO', 'AX', 'IY', 'EH', 'IH', 'AY', 'IX', 'AA', 'UW',
|
||||||
|
'UH', 'UX', 'OW', 'AW', 'OY', 'b', 'C', 'd', 'D', 'f', 'g', 'h', 'J', 'k',
|
||||||
|
'l', 'm', 'n', 'N', 'p', 'r', 's', 'S', 't', 'T', 'v', 'w', 'y', 'z', 'Z'
|
||||||
|
]
|
||||||
|
|
||||||
|
class ApplePhoneme(object):
|
||||||
|
"""docstring for ApplePhoneme."""
|
||||||
|
|
||||||
|
def __init__(self, phone, stress, vowel=False):
|
||||||
|
super(ApplePhoneme, self).__init__()
|
||||||
|
self.phone = phone
|
||||||
|
self.stress = stress
|
||||||
|
self.vowel = vowel
|
||||||
|
|
||||||
|
def __str__(self):
|
||||||
|
return (str(self.stress) if (self.vowel and self.stress>0) else '') + self.phone
|
||||||
|
|
||||||
|
def __repr__(self):
|
||||||
|
return "'{}'".format(str(self))
|
||||||
|
|
||||||
|
def adjust_stress(self):
|
||||||
|
self.stress = random.choice([i for i in range(3) if i != self.stress])
|
||||||
|
|
||||||
|
|
||||||
|
def parse_apple_phonemes(ph_str):
|
||||||
|
for i in range(len(ph_str)):
|
||||||
|
pref, rest = ph_str[:i + 1], ph_str[i + 1:]
|
||||||
|
if pref in apple_phonemes:
|
||||||
|
vowel = pref[0] in 'AEIOU'
|
||||||
|
return [ApplePhoneme(pref, 0, vowel)] + parse_apple_phonemes(rest)
|
||||||
|
elif pref[0].isdigit() and pref[1:] in apple_phonemes:
|
||||||
|
return [ApplePhoneme(pref[1:], int(pref[0]) , True)] + parse_apple_phonemes(rest)
|
||||||
|
elif not pref.isalnum():
|
||||||
|
return [ApplePhoneme(pref, 0, False)] + parse_apple_phonemes(rest)
|
||||||
|
return []
|
||||||
|
|
||||||
|
|
||||||
|
def similar_phoneme_word(ph_str):
|
||||||
|
phons = parse_apple_phonemes(ph_str)
|
||||||
|
vowels = [i for i in phons if i.vowel]
|
||||||
|
random.choice(vowels).adjust_stress()
|
||||||
|
return ''.join([str(i) for i in phons])
|
||||||
|
|
||||||
|
def similar_phoneme_phrase(ph_str):
|
||||||
|
return ' '.join([similar_phoneme_word(w) for w in ph_str.split()])
|
||||||
|
|
||||||
|
def similar_word(word_str):
|
||||||
|
similar = pronouncing.rhymes(word_str)
|
||||||
|
return random.choice(similar) if len(similar) > 0 else word_str
|
||||||
|
|
||||||
|
def similar_phrase(ph_str):
|
||||||
|
return ' '.join([similar_word(w) for w in ph_str.split()])
|
||||||
|
|
@ -0,0 +1,73 @@
|
||||||
|
import objc
|
||||||
|
from AppKit import *
|
||||||
|
from Foundation import NSURL
|
||||||
|
from PyObjCTools import AppHelper
|
||||||
|
from time import time
|
||||||
|
|
||||||
|
apple_phonemes = [
|
||||||
|
'%', '@', 'AE', 'EY', 'AO', 'AX', 'IY', 'EH', 'IH', 'AY', 'IX', 'AA', 'UW',
|
||||||
|
'UH', 'UX', 'OW', 'AW', 'OY', 'b', 'C', 'd', 'D', 'f', 'g', 'h', 'J', 'k',
|
||||||
|
'l', 'm', 'n', 'N', 'p', 'r', 's', 'S', 't', 'T', 'v', 'w', 'y', 'z', 'Z'
|
||||||
|
]
|
||||||
|
len(apple_phonemes)
|
||||||
|
|
||||||
|
speech_phoneme_data = []
|
||||||
|
|
||||||
|
class SpeechDelegate (NSObject):
|
||||||
|
def speechSynthesizer_willSpeakWord_ofString_(self, sender, word, text):
|
||||||
|
'''Called automatically when the application has launched'''
|
||||||
|
print("Speaking word {} in sentence {}".format(word,text))
|
||||||
|
|
||||||
|
def speechSynthesizer_willSpeakPhoneme_(self,sender,phoneme):
|
||||||
|
phon_ch = apple_phonemes[phoneme]
|
||||||
|
# print('first',speech_phoneme_data)
|
||||||
|
# prev_time = speech_phoneme_data[-1][1]
|
||||||
|
# print('prev_time',prev_time)
|
||||||
|
speech_phoneme_data.append((phon_ch,time()))
|
||||||
|
print("phoneme boundary for {} time {}".format(phon_ch,time()))
|
||||||
|
# NSApp().terminate_(self)
|
||||||
|
|
||||||
|
def speechSynthesizer_didFinishSpeaking_(self,synth,didFinishSpeaking):
|
||||||
|
speech_phoneme_data.append(('%',time()))
|
||||||
|
print("finished speaking time {}".format(time()))
|
||||||
|
diff_time = []
|
||||||
|
for i in range(len(speech_phoneme_data)-1):
|
||||||
|
dur = speech_phoneme_data[i+1][1] - speech_phoneme_data[i][1]
|
||||||
|
diff_time.append((speech_phoneme_data[i][0],dur))
|
||||||
|
print(diff_time)
|
||||||
|
|
||||||
|
# del SpeechDelegate
|
||||||
|
class Delegate (NSObject):
|
||||||
|
def applicationDidFinishLaunching_(self, aNotification):
|
||||||
|
'''Called automatically when the application has launched'''
|
||||||
|
print("Window, World!")
|
||||||
|
|
||||||
|
def windowWillClose_(self, aNotification):
|
||||||
|
'''Called automatically when the window is closed'''
|
||||||
|
print("Window has been closed")
|
||||||
|
# Terminate the application
|
||||||
|
NSApp().terminate_(self)
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
speech_delg = SpeechDelegate.alloc().init()
|
||||||
|
speech_delg.speechSynthesizer_didFinishSpeaking_('t',True)
|
||||||
|
voices = NSSpeechSynthesizer.availableVoices()
|
||||||
|
identifier = voices[2]
|
||||||
|
time()
|
||||||
|
alex_voice = NSSpeechSynthesizer.alloc().initWithVoice_(identifier)
|
||||||
|
alex_voice.setDelegate_(speech_delg)
|
||||||
|
alex_voice.startSpeakingString_("This is a test for speech synthesis generation")
|
||||||
|
# Create a new application instance ...
|
||||||
|
a=NSApplication.sharedApplication()
|
||||||
|
# ... and create its delgate. Note the use of the
|
||||||
|
# Objective C constructors below, because Delegate
|
||||||
|
# is a subcalss of an Objective C class, NSObject
|
||||||
|
delegate = Delegate.alloc().init()
|
||||||
|
# Tell the application which delegate object to use.
|
||||||
|
a.setDelegate_(delegate)
|
||||||
|
|
||||||
|
AppHelper.runEventLoop()
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
main()
|
||||||
Loading…
Reference in New Issue