如何使口袋狮身人面像模块更有效率？

Question

我尝试使用下面显示的python代码试用口袋狮身人面像和谷歌stt引擎：

import speech_recognition as sr
r = sr.Recognizer()
with sr.Microphone() as source:
    audio = r.adjust_for_ambient_noise(source)
    print('\n\n')
    print("Say something!")
    audio = r.listen(source,timeout=5)
t=r.recognize_google(audio)
s=r.recognize_sphinx(audio)
print('\n\n')
print('Google thinks that you said:',t)
print('Sphinx thinks that you said:',s)

代码的输入短语是：＆＃34;测试音频2录音＆＃34;

这是输出：

Say something!


Google thinks that you said: text audio two recording
Sphinx thinks that you said: this would you move it going to the fed

然而，通过口袋狮身人面像识别的语音非常差，甚至与我说的话都不相似......但谷歌的STt认为它很完美..无论如何都有提高口袋狮身人面像的语音检测质量。我不希望口袋狮身人面像非常完美，但所识别的单词听起来甚至听起来与我说的相似......

那么有没有办法改善口袋狮身人面像的质量........我刚为python3安装了Pocketsphinx和SpeechRecognition模块。