语音识别的基本框架
from win32com.client import constants
import os
import win32com.client
import pythoncom
class SpeechRecognition:
def __init__(self, wordsToAdd):
self.speaker = win32com.client.Dispatch("SAPI.SpVoice")
self.listener = win32com.client.Dispatch("SAPI.SpSharedRecognizer")
self.context = self.listener.CreateRecoContext()
self.grammar = self.context.CreateGrammar()
self.grammar.DictationSetState(0)
self.wordsRule = self.grammar.Rules.Add("wordsRule", constants.SRATopLevel + constants.SRADynamic, 0)
self.wordsRule.Clear()
[self.wordsRule.InitialState.AddWordTransition(None, word) for word in wordsToAdd]
self.grammar.Rules.Commit()
self.grammar.CmdSetRuleState("wordsRule", 1)
self.grammar.Rules.Commit()
self.eventHandler = ContextEvents(self.context)
self.say("Started successfully")
def say(self, phrase):
self.speaker.Speak(phrase)
class ContextEvents(win32com.client.getevents("SAPI.SpSharedRecoContext")):
def OnRecognition(self, StreamNumber, StreamPosition, RecognitionType, Result):
newResult = win32com.client.Dispatch(Result)
print("你在说 ", newResult.PhraseInfo.GetText())
cmd = newResult.PhraseInfo.GetText() #令cmd=接听到的语音,判断执行命令
if cmd == "计算器":
os.system("calc")
elif cmd == "程序和功能":
os.system("appwiz.cpl")
elif cmd == "证书管理":
os.system("certmgr.msc")
elif cmd == "启动字符映射表":
os.system("charmap")
elif cmd == "磁盘检查":
os.system("chkdsk.exe")
elif cmd == "打开磁盘清理工具":
os.system("cleanmgr")
elif cmd == "记事本":
os.system("notepad")
elif cmd == "写字板":
os.system("write")
elif cmd == "画图板":
os.system("mspaint")
elif cmd == "设置":
os.system("msconfig")
else:
print("我没听到你说啥")
if __name__ == '__main__':
wordsToAdd = ["关机", "取消关机", "记事本", # list中的语音
"画图板", "写字板", "计算器",
"程序和功能", "证书管理", "启动字符映射表",
"磁盘检查", "打开磁盘清理工具",
"设置"]
speechReco = SpeechRecognition(wordsToAdd)
while True:
pythoncom.PumpWaitingMessages()